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

    Neuronpedia

    INDEX
    Explanations

    .annotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .obs
    -0.08
    _stride
    -0.07
     coupled
    -0.07
    �
    -0.07
    .toastr
    -0.06
    occupation
    -0.06
    徒步
    -0.06
    ugu
    -0.06
    ☻
    -0.06
    景德
    -0.06
    POSITIVE LOGITS
    서
    0.09
    }*/↵
    0.07
    _EDIT
    0.07
    קרו
    0.07
     Hick
    0.07
    _PARAMS
    0.07
     MethodInfo
    0.07
     asking
    0.06
    Modules
    0.06
    珉
    0.06
    Act Density 0.002%

    No Known Activations