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

    Neuronpedia

    INDEX
    Explanations

    informal conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :semicolon
    -0.06
     tentang
    -0.06
    uye
    -0.06
    lish
    -0.06
     IOError
    -0.06
    .subtract
    -0.06
    י�
    -0.06
    ________________________________________________________________
    -0.06
     протяж
    -0.06
    badge
    -0.06
    POSITIVE LOGITS
    rej
    0.07
    odzi
    0.06
     easily
    0.06
     mote
    0.06
    ardi
    0.06
     अगर
    0.06
     ventil
    0.06
     sweeps
    0.06
     mereka
    0.06
     dáv
    0.06
    Act Density 0.012%

    No Known Activations