Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and conditions related to software licensing and usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    See definitions and licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themſelves
    -0.40
    忍不住
    -0.32
     入り
    -0.32
                                   
    -0.32
     Bratislava
    -0.31
     himſelf
    -0.30
    nikova
    -0.30
     itſelf
    -0.29
     Uttarakhand
    -0.29
    selves
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.84
     мәкал
    0.81
    WriteTagHelper
    0.78
     invokingState
    0.68
     Мексичка
    0.67
    Vidite
    0.67
     Administrativna
    0.66
     Italijani
    0.66
    SequentialGroup
    0.64
     linkovi
    0.64
    Act Density 2.944%

    No Known Activations