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

    Neuronpedia

    INDEX
    Explanations

    Death and execution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ываются
    -0.07
    struk
    -0.07
    地区
    -0.06
    치는
    -0.06
     Зав
    -0.06
    털
    -0.06
     importantes
    -0.06
     Tos
    -0.06
    eten
    -0.06
    -dir
    -0.06
    POSITIVE LOGITS
    ................................................................
    0.07
     perpetrated
    0.06
    UTION
    0.06
    bcrypt
    0.06
    -mf
    0.06
     criminal
    0.06
     Hollow
    0.06
     onay
    0.06
    :<
    0.06
    Byte
    0.06
    Act Density 0.017%

    No Known Activations