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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achievements and statistics

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

    past actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.49
    y
    -0.40
    Parcelable
    -0.39
    ther
    -0.38
     met
    -0.37
    gh
    -0.36
     .
    -0.36
     side
    -0.36
    q
    -0.35
    qu
    -0.35
    POSITIVE LOGITS
     itſelf
    0.81
     ſta
    0.80
    ſelves
    0.77
     ſche
    0.77
    ſelf
    0.75
     ſch
    0.74
    principalTable
    0.74
     faſt
    0.71
     Verſ
    0.69
     myſelf
    0.68
    Act Density 0.278%

    No Known Activations