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

    Neuronpedia

    INDEX
    Explanations

    consent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jich
    -0.07
     hayata
    -0.07
     �
    -0.07
    siblings
    -0.07
    ционного
    -0.07
     Live
    -0.07
    ンバー
    -0.07
     suất
    -0.06
    kový
    -0.06
     nikdo
    -0.06
    POSITIVE LOGITS
     bliss
    0.06
    	last
    0.06
     hoe
    0.06
    Odd
    0.06
     paren
    0.06
     toddler
    0.06
    	Type
    0.06
     Rid
    0.06
     ask
    0.06
    olla
    0.06
    Act Density 0.003%

    No Known Activations