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

    Neuronpedia

    INDEX
    Explanations

    programming function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    »،
    0.26
    lín
    0.26
    痱
    0.26
    unikasi
    0.25
     Elektrokhimiya
    0.25
     एक्सरे
    0.24
    positroid
    0.24
    螫
    0.24
     इतर
    0.23
     피부
    0.23
    POSITIVE LOGITS
     with
    0.37
    with
    0.31
    ↵
    0.30
            
    0.29
     at
    0.29
     settings
    0.29
     string
    0.28
     in
    0.28
     (
    0.28
    ({
    0.28
    Act Density 0.504%

    No Known Activations