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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	App
    -0.07
    undles
    -0.06
    ви
    -0.06
     hacked
    -0.06
    .Template
    -0.06
    uil
    -0.06
     puppet
    -0.06
    /ge
    -0.06
    .functional
    -0.06
     Bus
    -0.06
    POSITIVE LOGITS
     contraception
    0.07
     nad
    0.07
     danmark
    0.07
     "
    0.07
     Quận
    0.07
    _softc
    0.06
     těl
    0.06
     crush
    0.06
     Clara
    0.06
    เคราะห
    0.06
    Act Density 0.000%

    No Known Activations