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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,node
    -0.07
    触れ
    -0.07
    つの
    -0.07
    ┱
    -0.07
    _COMPARE
    -0.06
     telah
    -0.06
    🛵
    -0.06
     refriger
    -0.06
    䎃
    -0.06
     Strateg
    -0.06
    POSITIVE LOGITS
     Manufacturer
    0.07
    呕
    0.07
     whence
    0.07
     ')↵
    0.07
     ind
    0.06
    Hex
    0.06
    bool
    0.06
    nh
    0.06
    tre
    0.06
    ROM
    0.06
    Act Density 0.000%

    No Known Activations