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

    Neuronpedia

    INDEX
    Explanations

    potential or capability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abyrin
    -0.07
     HinderedRotor
    -0.07
     undone
    -0.07
     outsiders
    -0.06
    סקר
    -0.06
     Midlands
    -0.06
     Dimit
    -0.06
    纴
    -0.06
     famine
    -0.06
    WithName
    -0.06
    POSITIVE LOGITS
    gap
    0.08
    Wow
    0.08
     free
    0.08
    فض
    0.08
    cats
    0.07
    وال
    0.07
    ebx
    0.07
    粮食
    0.07
     rewrite
    0.07
    Est
    0.07
    Act Density 0.110%

    No Known Activations