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

    Neuronpedia

    INDEX
    Explanations

    Murder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inactive
    -0.08
     inactive
    -0.08
     Rasmussen
    -0.08
     buckle
    -0.08
    udal
    -0.07
     visc
    -0.07
    Inactive
    -0.07
    _userdata
    -0.07
    ‌గా
    -0.07
     zase
    -0.07
    POSITIVE LOGITS
     Warr
    0.09
     murder
    0.09
     mysteries
    0.09
     mystery
    0.08
     perpetr
    0.08
    กรรม
    0.08
     interpersonal
    0.08
     ordinance
    0.08
    版
    0.08
    يين
    0.08
    Act Density 0.007%

    No Known Activations