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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Form
    -0.07
     листоп
    -0.07
     Mana
    -0.06
    ニュ
    -0.06
    ucus
    -0.06
     pl
    -0.06
     Bed
    -0.06
     территор
    -0.06
    /form
    -0.06
    jb
    -0.06
    POSITIVE LOGITS
     Guide
    0.07
     }],↵
    0.07
     IMD
    0.07
     });↵↵↵
    0.06
    ์ได
    0.06
    _colour
    0.06
    드는
    0.06
    aviours
    0.06
    **↵
    0.06
    ynthesis
    0.06
    Act Density 0.003%

    No Known Activations