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

    Neuronpedia

    INDEX
    Explanations

    text reminiscing about the past

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Was
    -0.99
     was
    -0.96
    Was
    -0.94
     were
    -0.90
    was
    -0.88
     Were
    -0.79
     Did
    -0.74
     wasn
    -0.71
    Were
    -0.71
    were
    -0.69
    POSITIVE LOGITS
    čuje
    0.72
     can
    0.71
    LookAnd
    0.69
     are
    0.64
    cannot
    0.64
     cannot
    0.63
     is
    0.61
    addContainerGap
    0.60
     muſt
    0.59
    ApiModel
    0.59
    Act Density 3.173%

    No Known Activations