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

    Neuronpedia

    INDEX
    Explanations

    technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fil
    -0.28
    è®°
    -0.26
    pth
    -0.26
     cer
    -0.24
    -height
    -0.24
    wal
    -0.24
    å°ļ书
    -0.24
    çĮľ
    -0.24
    溺
    -0.24
    chein
    -0.24
    POSITIVE LOGITS
    ment
    0.28
    ylim
    0.27
     hyper
    0.26
    ä»ĵ
    0.25
    ardy
    0.25
    .Static
    0.25
    CKET
    0.25
     grounding
    0.25
    Chain
    0.25
    ión
    0.24
    Act Density 0.006%

    No Known Activations