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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Touches
    -0.07
    ياه
    -0.06
    _LIGHT
    -0.06
     degree
    -0.06
    htaking
    -0.06
     laps
    -0.06
     chẳng
    -0.05
    神
    -0.05
     cít
    -0.05
    ammable
    -0.05
    POSITIVE LOGITS
     Trim
    0.08
    _aligned
    0.07
    ???↵↵
    0.07
    Moreover
    0.06
    aira
    0.06
    592
    0.06
     Pf
    0.06
    /App
    0.06
     strategies
    0.06
     carrera
    0.06
    Act Density 0.006%

    No Known Activations