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

    Neuronpedia

    INDEX
    Explanations

    Josh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sudden
    -0.08
    🚆
    -0.08
    ;++
    -0.08
    皛
    -0.07
     addButton
    -0.07
    entes
    -0.07
    terrain
    -0.07
    เกร
    -0.07
     Alert
    -0.07
     Straßen
    -0.07
    POSITIVE LOGITS
    _Details
    0.07
     exquisite
    0.07
     Marvel
    0.07
     magnets
    0.07
    ulously
    0.07
    	k
    0.06
     Kom
    0.06
    marsh
    0.06
    當時
    0.06
    魍
    0.06
    Act Density 0.003%

    No Known Activations