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

    Neuronpedia

    INDEX
    Explanations

    specific contexts and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uf
    0.42
    Bureau
    0.42
    禹
    0.42
     Bureau
    0.38
     unfilled
    0.37
    antec
    0.37
    ungg
    0.36
    тивний
    0.36
    ⇩
    0.36
     thừa
    0.35
    POSITIVE LOGITS
    作為
    0.42
     যতই
    0.41
    作为
    0.40
     Therapy
    0.40
     প্রথমবারের
    0.39
     fugiat
    0.38
     carpenter
    0.38
    是他
    0.38
     Drama
    0.38
    orni
    0.38
    Act Density 0.000%

    No Known Activations