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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _information
    -0.07
    _s
    -0.07
     ген
    -0.07
    Nil
    -0.06
     open
    -0.06
    ’h
    -0.06
     Traff
    -0.06
     deterior
    -0.06
     sections
    -0.06
    .Rec
    -0.06
    POSITIVE LOGITS
    866
    0.07
     ayında
    0.07
    _PROXY
    0.06
    ULT
    0.06
    LOY
    0.06
    basename
    0.06
    BCM
    0.06
    گری
    0.06
     nikdy
    0.06
     때문에
    0.06
    Act Density 0.011%

    No Known Activations