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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cs
    -0.06
    c
    -0.06
     grave
    -0.06
    Splash
    -0.06
     pulses
    -0.06
    �
    -0.06
    Ya
    -0.06
     nombres
    -0.06
     випад
    -0.06
     overposting
    -0.06
    POSITIVE LOGITS
     증가
    0.07
    isson
    0.06
     effected
    0.06
     přip
    0.06
     Discussions
    0.06
     alg
    0.06
     kidnapping
    0.06
     Requirement
    0.06
    (([
    0.06
    $fields
    0.06
    Act Density 0.021%

    No Known Activations