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

    Neuronpedia

    INDEX
    Explanations

    murder mystery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Khr
    -0.09
    _requests
    -0.07
     net
    -0.07
     responsive
    -0.07
     repetitive
    -0.07
    REQ
    -0.07
    _chunk
    -0.07
    stu
    -0.07
     mì
    -0.07
     constants
    -0.07
    POSITIVE LOGITS
     murderous
    0.10
     culp
    0.10
     murder
    0.09
     accusation
    0.09
    Everyone
    0.09
     everyone's
    0.09
     हत्या
    0.09
     murderer
    0.09
     suç
    0.09
    urder
    0.09
    Act Density 0.027%

    No Known Activations