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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usa
    -0.07
    hz
    -0.07
     ag
    -0.07
    醢
    -0.07
    Ў
    -0.06
    Website
    -0.06
    نغ
    -0.06
    Android
    -0.06
    dong
    -0.06
    visor
    -0.06
    POSITIVE LOGITS
     repl
    0.08
     Jacket
    0.08
     layouts
    0.08
    病变
    0.07
     demolition
    0.07
     filtration
    0.07
    .DateField
    0.06
    rical
    0.06
     metic
    0.06
     mappings
    0.06
    Act Density 0.000%

    No Known Activations