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

    Neuronpedia

    INDEX
    Explanations

    role-playing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prevalence
    -0.08
    _coordinates
    -0.07
     calam
    -0.06
     bedroom
    -0.06
     branch
    -0.06
    _character
    -0.06
     negativity
    -0.06
    >}
    -0.06
     domain
    -0.06
    비
    -0.06
    POSITIVE LOGITS
     premiered
    0.07
     свид
    0.06
    Qty
    0.06
    .swift
    0.06
    .degree
    0.06
     khoản
    0.06
     jä
    0.06
     ↵		↵
    0.06
     کارخانه
    0.06
    -org
    0.06
    Act Density 0.139%

    No Known Activations