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

    Neuronpedia

    INDEX
    Explanations

    text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addLine
    0.42
     લો
    0.38
    >>();
    0.37
     Rehabilit
    0.37
     Crash
    0.36
    ޟ
    0.36
    ক্য
    0.36
    бую
    0.36
     بشر
    0.36
    webapp
    0.36
    POSITIVE LOGITS
    മ്
    0.38
     meskipun
    0.37
     principes
    0.37
     respect
    0.36
    στ
    0.36
    hyun
    0.36
    mode
    0.36
     ressembl
    0.36
     გა
    0.35
     Raya
    0.35
    Act Density 0.000%

    No Known Activations