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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Merit
    -0.06
     произош
    -0.06
    Ά
    -0.06
     πρέπει
    -0.06
     Enables
    -0.06
     emphasized
    -0.06
    pk
    -0.06
    449
    -0.06
    /back
    -0.06
     ');↵↵
    -0.06
    POSITIVE LOGITS
     Mississippi
    0.07
    Transformation
    0.06
    sgiving
    0.06
    .tabControl
    0.06
     ListItem
    0.06
     IP
    0.06
    .ACCESS
    0.06
    .uint
    0.06
     (*)
    0.06
    sweet
    0.06
    Act Density 0.004%

    No Known Activations