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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     אם
    -0.07
    0
    -0.07
    argon
    -0.07
     denounced
    -0.07
    _LD
    -0.07
     pellets
    -0.07
     incest
    -0.06
     priests
    -0.06
    .pres
    -0.06
    inne
    -0.06
    POSITIVE LOGITS
    crawler
    0.07
    🅼
    0.07
    .dis
    0.07
    さま
    0.07
    允
    0.06
    /
↵
    0.06
    上がり
    0.06
    _
↵
    0.06
    精英
    0.06
     sliding
    0.06
    Act Density 0.099%

    No Known Activations