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

    Neuronpedia

    INDEX
    Explanations

    -phase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AreaView
    -0.08
    =username
    -0.07
     '{@
    -0.07
    )throws
    -0.07
     vulnerable
    -0.07
    [at
    -0.07
    .bumptech
    -0.07
     commonplace
    -0.07
    犀
    -0.06
    _we
    -0.06
    POSITIVE LOGITS
    ㎘
    0.08
     עכשיו
    0.07
    	memcpy
    0.06
    лич
    0.06
     Alumni
    0.06
     bubb
    0.06
    aya
    0.06
    ”.↵↵
    0.06
     País
    0.06
     informing
    0.06
    Act Density 0.004%

    No Known Activations