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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tí
    -0.07
    to
    -0.07
    ูน
    -0.06
    ุง
    -0.06
    cu
    -0.06
    itably
    -0.06
    _predicted
    -0.06
    itted
    -0.06
    artner
    -0.06
    Neal
    -0.06
    POSITIVE LOGITS
     Meth
    0.08
     +%
    0.07
     kop
    0.07
    -cent
    0.06
     Ramp
    0.06
     εργ
    0.06
    Should
    0.06
     maneuver
    0.06
     방법
    0.06
    (angle
    0.06
    Act Density 0.028%

    No Known Activations