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

    Neuronpedia

    INDEX
    Explanations

    words related to hypothetical situations, past actions, and desires

    oai_token-act-pair · gemini-2.0-flash

    life, hypothetical scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.88
    ſelf
    -0.81
     Jefus
    -0.79
     pleaſure
    -0.76
    ViewFeatures
    -0.76
    ſelves
    -0.75
    ględ
    -0.74
     Theſe
    -0.73
     faſt
    -0.72
    maßen
    -0.70
    POSITIVE LOGITS
     am
    0.59
    noch
    0.53
    kund
    0.49
     yourself
    0.48
     ander
    0.48
    Myself
    0.48
     myself
    0.47
    ffin
    0.47
     Te
    0.46
    bild
    0.46
    Act Density 4.215%

    No Known Activations