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
    Coding
    -0.07
    threat
    -0.07
    _HOME
    -0.06
    .Lines
    -0.06
     Roo
    -0.06
    FAILED
    -0.06
    CCCCCC
    -0.06
    |null
    -0.06
    Distance
    -0.06
    _BROWSER
    -0.06
    POSITIVE LOGITS
    ώρα
    0.07
     DL
    0.06
    usic
    0.06
     spirituality
    0.06
     aus
    0.06
     evac
    0.06
    ünd
    0.06
     nymph
    0.06
    άνα
    0.06
    !)
    0.06
    Act Density 0.051%

    No Known Activations