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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     take
    -0.07
    783
    -0.07
    _scalar
    -0.07
     algorithm
    -0.07
     Arthropoda
    -0.07
    ısıt
    -0.06
     whatever
    -0.06
    trap
    -0.06
     body
    -0.06
     adult
    -0.06
    POSITIVE LOGITS
     Fucking
    0.08
     freaking
    0.08
     fucking
    0.07
     referencedColumnName
    0.07
    'clock
    0.06
    (EIF
    0.06
    comments
    0.06
    Vu
    0.06
     fracking
    0.06
    morgan
    0.06
    Act Density 0.005%

    No Known Activations