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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dependencies
    -0.07
     silently
    -0.07
     Fault
    -0.07
     standard
    -0.06
    .cost
    -0.06
     academics
    -0.06
    .Expression
    -0.06
     invokes
    -0.06
     distractions
    -0.06
    .Constraint
    -0.06
    POSITIVE LOGITS
     χωρίς
    0.06
    .Multi
    0.06
    ollect
    0.06
     šest
    0.06
    .ReactNode
    0.06
     hodně
    0.06
    _ACTIONS
    0.06
     моря
    0.06
    ือข
    0.06
     يك
    0.06
    Act Density 0.022%

    No Known Activations