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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _days
    -0.07
    орони
    -0.07
    Prop
    -0.07
    Φ
    -0.07
    angs
    -0.07
     tours
    -0.07
    -mails
    -0.06
     Reynolds
    -0.06
    Postal
    -0.06
    $a
    -0.06
    POSITIVE LOGITS
     Lesser
    0.06
     outgoing
    0.06
    ":"","
    0.06
     salv
    0.06
    LD
    0.06
     전국
    0.06
    Persona
    0.06
    .chars
    0.05
    (gr
    0.05
     honestly
    0.05
    Act Density 0.022%

    No Known Activations