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

    Neuronpedia

    INDEX
    Explanations

    ores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unbind
    -0.06
    をつ
    -0.06
    acman
    -0.06
    esture
    -0.05
     quite
    -0.05
     crossAxisAlignment
    -0.05
     fatally
    -0.05
     Edmund
    -0.05
    	mat
    -0.05
     सबस
    -0.05
    POSITIVE LOGITS
    Fc
    0.07
    /black
    0.07
     heirs
    0.07
    -ish
    0.07
     couleur
    0.07
    oire
    0.07
    風
    0.07
    حه
    0.06
     Log
    0.06
    ję
    0.06
    Act Density 0.001%

    No Known Activations