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

    Neuronpedia

    INDEX
    Explanations

    because

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Say
    -0.07
     infantry
    -0.07
    interop
    -0.07
     Nicol
    -0.06
    recover
    -0.06
     Shorts
    -0.06
    .pan
    -0.06
     veil
    -0.06
    /sn
    -0.06
     Slayer
    -0.06
    POSITIVE LOGITS
     because
    0.08
     λίγ
    0.07
     uncon
    0.07
    uest
    0.07
     mrb
    0.07
     freedom
    0.06
     EdgeInsets
    0.06
    ston
    0.06
    raising
    0.06
     Minist
    0.06
    Act Density 0.026%

    No Known Activations