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

    Neuronpedia

    INDEX
    Explanations

    angled brackets containing names and code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CrossRef
    -0.48
    rd
    -0.47
    ler
    -0.46
    mp
    -0.45
    Â
    -0.44
    ir
    -0.42
    cp
    -0.42
    rr
    -0.41
    odor
    -0.41
    を経
    -0.41
    POSITIVE LOGITS
    TintMode
    1.02
     transfieras
    0.91
    ########.
    0.90
     تانيه
    0.88
    WebVitals
    0.85
     saites
    0.84
    AndEndTag
    0.84
    tagHelperRunner
    0.83
    OGND
    0.82
    HostException
    0.81
    Act Density 0.774%

    No Known Activations