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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แนะ
    -0.06
     Sand
    -0.06
    adi
    -0.06
     Bans
    -0.06
    Các
    -0.06
     nuclei
    -0.06
     причин
    -0.06
     요청
    -0.06
    brane
    -0.06
     hap
    -0.06
    POSITIVE LOGITS
    —↵↵
    0.07
     모르
    0.06
     еж
    0.06
    ())↵
    0.06
     Butt
    0.06
    ，我
    0.06
    같
    0.06
     MÜ
    0.06
     mio
    0.06
    Hopefully
    0.06
    Act Density 0.111%

    No Known Activations