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

    Neuronpedia

    INDEX
    Explanations

    honesty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COST
    -0.07
    _smooth
    -0.07
     dosud
    -0.07
    -loader
    -0.07
    .addWidget
    -0.06
    师
    -0.06
     sopr
    -0.06
    (det
    -0.06
     커
    -0.06
    虎
    -0.06
    POSITIVE LOGITS
    став
    0.07
     Exped
    0.07
    Create
    0.06
    _ABORT
    0.06
    MITTED
    0.06
    puties
    0.06
     Chron
    0.06
     leaves
    0.06
    �
    0.06
     Create
    0.06
    Act Density 0.015%

    No Known Activations