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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Live
    -0.06
    _accept
    -0.06
    <Value
    -0.06
    PED
    -0.06
     Vision
    -0.06
    riot
    -0.06
    י�
    -0.06
     repell
    -0.06
     Acc
    -0.06
    >Your
    -0.06
    POSITIVE LOGITS
    logout
    0.07
    _adc
    0.06
     Kara
    0.06
    _UDP
    0.06
    )!↵
    0.06
    owitz
    0.06
    orden
    0.06
    _geo
    0.06
    цеп
    0.06
     Riverside
    0.06
    Act Density 0.001%

    No Known Activations