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

    Neuronpedia

    INDEX
    Explanations

    murder

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getCode
    -0.07
    Branch
    -0.07
    -rays
    -0.06
     pathway
    -0.06
     blossom
    -0.06
     resource
    -0.06
    _mapped
    -0.06
    阶段
    -0.06
     seemed
    -0.06
    _fake
    -0.06
    POSITIVE LOGITS
     Murder
    0.08
     murder
    0.08
     "}\
    0.07
    )data
    0.07
     nerv
    0.07
     Killer
    0.07
    \\
    0.06
    府
    0.06
    废
    0.06
     mur
    0.06
    Act Density 0.007%

    No Known Activations