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

    Neuronpedia

    INDEX
    Explanations

    academics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ỡ
    -0.07
    曦
    -0.06
    xee
    -0.06
     나는
    -0.06
     hát
    -0.06
     nét
    -0.06
    fällig
    -0.06
    寻
    -0.06
    תשוב
    -0.06
     개
    -0.06
    POSITIVE LOGITS
    continent
    0.09
    ,K
    0.07
    0.07
    _ZERO
    0.07
    Prob
    0.07
     accusing
    0.07
     plaats
    0.07
    ,P
    0.07
     Rehab
    0.07
    expiration
    0.07
    Act Density 0.047%

    No Known Activations