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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slider
    -0.06
     bends
    -0.06
    stype
    -0.06
    Voltage
    -0.06
    walk
    -0.06
    /features
    -0.06
    unkt
    -0.06
    /pdf
    -0.06
     walk
    -0.06
     slider
    -0.06
    POSITIVE LOGITS
     Qualcomm
    0.07
    /ex
    0.07
    �
    0.07
     hostage
    0.07
    _FETCH
    0.07
    _busy
    0.06
    ipsis
    0.06
     revelations
    0.06
    _fin
    0.06
    _Main
    0.06
    Act Density 0.015%

    No Known Activations