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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coerc
    -0.08
     ort
    -0.08
    192
    -0.07
     పోల
    -0.07
     Ort
    -0.07
     quo
    -0.07
    итив
    -0.07
     Mormon
    -0.07
     plein
    -0.07
    Verb
    -0.07
    POSITIVE LOGITS
     moon
    0.09
    ọd
    0.09
    -reaching
    0.09
     profundo
    0.09
     লাভ
    0.08
     profunda
    0.08
     admiration
    0.08
     enr
    0.08
     profundas
    0.08
     entw
    0.08
    Act Density 0.086%

    No Known Activations