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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    šk
    -0.08
    Johnson
    -0.07
     області
    -0.07
    _ui
    -0.07
    ik
    -0.07
    ape
    -0.07
    obj
    -0.07
     Об
    -0.06
     thru
    -0.06
     Johnson
    -0.06
    POSITIVE LOGITS
     tě
    0.07
    herited
    0.06
    _MULTI
    0.06
     trium
    0.06
    _dump
    0.06
     &_
    0.06
     gsl
    0.06
    otp
    0.06
     })}↵
    0.06
     _|
    0.06
    Act Density 0.209%

    No Known Activations