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

    Neuronpedia

    INDEX
    Explanations

    Code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Charity
    -0.07
    .When
    -0.07
     Kingdom
    -0.07
     yaşam
    -0.07
     aun
    -0.06
     SCHOOL
    -0.06
     dusty
    -0.06
    ù
    -0.06
     Ninth
    -0.06
     When
    -0.06
    POSITIVE LOGITS
    cond
    0.07
     γ
    0.07
    Previously
    0.07
     endforeach
    0.06
     contentious
    0.06
    %">↵
    0.06
    _ble
    0.06
     hintText
    0.06
     newName
    0.06
     tekn
    0.06
    Act Density 0.028%

    No Known Activations