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

    Neuronpedia

    INDEX
    Explanations

    Descriptive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adium
    -0.07
     Gate
    -0.07
     retreat
    -0.07
     identity
    -0.07
    -door
    -0.06
     deceit
    -0.06
    гал
    -0.06
    -slot
    -0.06
    _EN
    -0.06
    <char
    -0.06
    POSITIVE LOGITS
    767
    0.07
    869
    0.07
    	ERROR
    0.06
     bt
    0.06
    ABL
    0.06
    LastError
    0.06
    ليف
    0.06
    였
    0.06
    散
    0.06
    _ALWAYS
    0.06
    Act Density 0.000%

    No Known Activations