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

    Neuronpedia

    INDEX
    Explanations

    values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FULL
    -0.07
     потому
    -0.07
     grandson
    -0.07
     deformation
    -0.07
     طرف
    -0.07
     cpu
    -0.06
    assignment
    -0.06
    enance
    -0.06
    _frag
    -0.06
     پسر
    -0.06
    POSITIVE LOGITS
     values
    0.14
     Values
    0.11
    Values
    0.11
    values
    0.10
    -values
    0.08
     valores
    0.07
    $values
    0.07
     hodnoty
    0.06
    Vals
    0.06
    mounted
    0.06
    Act Density 0.027%

    No Known Activations