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

    Neuronpedia

    INDEX
    Explanations

    fx and .Common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ാം
    -0.08
     habitants
    -0.08
    /ic
    -0.07
    acho
    -0.07
    asure
    -0.07
    ination
    -0.07
     évid
    -0.07
     adequate
    -0.07
     qualitative
    -0.07
    verture
    -0.07
    POSITIVE LOGITS
     citing
    0.08
    .
↵
    0.08
     해야
    0.08
     kommentar
    0.08
    ↵
↵
↵
    0.08
     Winston
    0.08
     porn
    0.07
     komment
    0.07
     koment
    0.07
     bouts
    0.07
    Act Density 0.000%

    No Known Activations