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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [y
    -0.06
     *)&
    -0.06
    ?>&
    -0.06
     Tops
    -0.06
    _L
    -0.06
    "L
    -0.06
     computing
    -0.06
    .=
    -0.06
     افزایش
    -0.06
     〃
    -0.06
    POSITIVE LOGITS
    }()↵
    0.07
    CPP
    0.06
    =forms
    0.06
    _DEV
    0.06
    }()↵↵
    0.06
     Helps
    0.06
     खतर
    0.06
    -non
    0.06
     normalize
    0.06
     endured
    0.06
    Act Density 0.001%

    No Known Activations