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

    Neuronpedia

    INDEX
    Explanations

    code/sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bracelet
    -0.07
    enus
    -0.07
    列表
    -0.07
    figcaption
    -0.06
    ez
    -0.06
    роп
    -0.06
     era
    -0.06
    WebView
    -0.06
    ρκεια
    -0.06
    anz
    -0.06
    POSITIVE LOGITS
     Employ
    0.07
     Bair
    0.07
     ineffective
    0.07
    ToSelector
    0.07
     conexión
    0.06
     بالم
    0.06
     Coul
    0.06
     ADVISED
    0.06
    phabet
    0.06
     residue
    0.06
    Act Density 2.134%

    No Known Activations