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

    Neuronpedia

    INDEX
    Explanations

    phrases related to application and implementation of processes or information

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

    archaic and non-standard spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    semantics
    -0.49
    getDoctrine
    -0.48
     ')[
    -0.43
     потеря
    -0.42
     ")[
    -0.42
    badah
    -0.41
    TestBed
    -0.40
    pad
    -0.40
    ka
    -0.39
    Gambas
    -0.39
    POSITIVE LOGITS
    Datuak
    0.64
    ſelf
    0.55
    ſelves
    0.53
     quæ
    0.52
     poffible
    0.52
     chofe
    0.49
     neceff
    0.49
    何より
    0.49
     fubject
    0.48
     myſelf
    0.48
    Act Density 0.053%

    No Known Activations