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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Almost
    -0.07
     tráv
    -0.07
    Whether
    -0.07
     excl
    -0.06
    allows
    -0.06
    sthrough
    -0.06
     amphib
    -0.06
    مبر
    -0.05
    _Task
    -0.05
    /single
    -0.05
    POSITIVE LOGITS
     Viewer
    0.07
    EDIT
    0.07
    (sa
    0.07
    ニー
    0.07
    .metric
    0.07
    _mesh
    0.07
     crown
    0.06
     cryptocurrency
    0.06
    engeance
    0.06
    credits
    0.06
    Act Density 0.099%

    No Known Activations