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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ])**
    -0.08
     zdroj
    -0.07
    ")↵↵
    -0.07
     driveway
    -0.07
     rainbow
    -0.06
     cx
    -0.06
    callback
    -0.06
    ací
    -0.06
    _GOOD
    -0.06
    ấp
    -0.06
    POSITIVE LOGITS
     absolut
    0.07
     Pharm
    0.07
    .onSubmit
    0.06
     حضرت
    0.06
    _unsigned
    0.06
    /stat
    0.06
     extr
    0.06
     sympath
    0.06
     Staten
    0.06
     Reflect
    0.06
    Act Density 0.002%

    No Known Activations