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

    Neuronpedia

    INDEX
    Explanations

    website layouts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exp
    -0.07
    Hey
    -0.07
     αν
    -0.07
    .contacts
    -0.06
     allocate
    -0.06
     gradual
    -0.06
     old
    -0.06
     soudu
    -0.06
     trapped
    -0.06
     presents
    -0.06
    POSITIVE LOGITS
    олаг
    0.06
    롱
    0.06
     ={
    0.06
     gezocht
    0.06
    ωτερ
    0.06
     appendString
    0.06
    _TIMESTAMP
    0.06
     geme
    0.06
    违
    0.06
    ,end
    0.06
    Act Density 0.029%

    No Known Activations