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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MatTable
    -0.06
     rfl
    -0.06
     boton
    -0.05
    atal
    -0.05
     стат
    -0.05
    atte
    -0.05
     flotation
    -0.05
    actical
    -0.05
    _AC
    -0.05
     astronomical
    -0.05
    POSITIVE LOGITS
     ado
    0.07
    '<
    0.07
    _threshold
    0.07
    :text
    0.07
    一点
    0.07
    Loop
    0.07
     громадян
    0.07
    Lines
    0.06
    โท
    0.06
     ");
↵
    0.06
    Act Density 0.096%

    No Known Activations