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

    Neuronpedia

    INDEX
    Explanations

    expressing thanks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ngrx
    -0.06
    sap
    -0.06
    Actions
    -0.06
    _contr
    -0.06
     Deputy
    -0.06
     vamp
    -0.06
    Priority
    -0.06
    Wildcard
    -0.06
    ційних
    -0.06
    ']/
    -0.06
    POSITIVE LOGITS
    ัดส
    0.07
     списка
    0.07
     nicely
    0.06
     bufsize
    0.06
    мы
    0.06
     christ
    0.06
     part
    0.06
    avoid
    0.06
     ειδ
    0.06
     acknowledged
    0.06
    Act Density 0.044%

    No Known Activations