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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    th
    -0.07
    ifact
    -0.06
    dup
    -0.06
    anas
    -0.06
     RD
    -0.06
     riff
    -0.06
     zel
    -0.06
    ungal
    -0.06
     veut
    -0.06
     fichier
    -0.06
    POSITIVE LOGITS
     Motorcycle
    0.07
     Holden
    0.06
     slipped
    0.06
    Within
    0.06
    .getFile
    0.06
    ><?=$
    0.06
    Permission
    0.06
    ');↵↵↵
    0.06
    abies
    0.06
     sensation
    0.06
    Act Density 0.010%

    No Known Activations