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

    Neuronpedia

    INDEX
    Explanations

    Book descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เว
    -0.07
     الدول
    -0.06
     успеш
    -0.06
    _layers
    -0.06
     ParameterDirection
    -0.06
    ่าว
    -0.06
     stripped
    -0.06
    	settings
    -0.06
     officially
    -0.06
     là
    -0.06
    POSITIVE LOGITS
    uum
    0.07
     cał
    0.06
    *****↵
    0.06
    -table
    0.06
     μ
    0.06
    ับค
    0.06
    Dem
    0.06
    .comp
    0.06
    _coeffs
    0.06
     цьому
    0.06
    Act Density 0.020%

    No Known Activations