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

    Neuronpedia

    INDEX
    Explanations

    named entities/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :[↵
    -0.07
     �
    -0.07
    说的
    -0.07
     Sing
    -0.06
     abstract
    -0.06
    ania
    -0.06
     devis
    -0.06
    Anc
    -0.06
    Pix
    -0.06
    กรรมการ
    -0.06
    POSITIVE LOGITS
     approx
    0.06
    quisar
    0.06
     haf
    0.06
     Wol
    0.06
    _ADMIN
    0.05
     міся
    0.05
    h
    0.05
    HostName
    0.05
     kep
    0.05
     lateral
    0.05
    Act Density 0.168%

    No Known Activations