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

    Neuronpedia

    INDEX
    Explanations

    toxicology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尊
    -0.07
     sensual
    -0.06
    ishing
    -0.06
     folded
    -0.06
     Kr
    -0.06
     Vish
    -0.06
    errer
    -0.06
     drop
    -0.06
     longstanding
    -0.06
    으니
    -0.06
    POSITIVE LOGITS
     //$
    0.07
    .bat
    0.07
     Cherry
    0.07
     muy
    0.07
     Everyone
    0.07
     Brighton
    0.06
    *sizeof
    0.06
     město
    0.06
    ]+$
    0.06
    /Search
    0.06
    Act Density 0.017%

    No Known Activations