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

    Neuronpedia

    INDEX
    Explanations

    However

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atlas
    -0.07
     breeding
    -0.06
    átis
    -0.06
    9
    -0.06
     sto
    -0.06
    ыџN
    -0.06
    .step
    -0.06
    ávací
    -0.06
    th
    -0.06
     top
    -0.06
    POSITIVE LOGITS
     However
    0.13
     however
    0.12
    However
    0.11
    Harry
    0.08
    scar
    0.08
     활용
    0.08
    however
    0.08
    هار
    0.08
    HM
    0.08
    NSMutable
    0.08
    Act Density 0.096%

    No Known Activations