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

    Neuronpedia

    INDEX
    Explanations

    Spanish text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Di
    -0.07
     Di
    -0.07
    Philadelphia
    -0.07
    ädchen
    -0.06
    475
    -0.06
     SQUARE
    -0.06
    067
    -0.06
    �
    -0.06
    Virginia
    -0.06
     icons
    -0.06
    POSITIVE LOGITS
    _YEAR
    0.07
    )
↵
↵
    0.06
         
↵
    0.06
    ner
    0.06
    ;%
    0.06
    .bundle
    0.06
     distracting
    0.06
    ΑΠ
    0.06
     (%)
    0.06
    ("("
    0.06
    Act Density 0.001%

    No Known Activations