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

    Neuronpedia

    INDEX
    Explanations

    Prophet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tod
    -0.07
     orchestra
    -0.07
     muž
    -0.07
     SAR
    -0.07
    -wife
    -0.07
     tox
    -0.07
     ey
    -0.07
    woods
    -0.07
     FO
    -0.06
    주
    -0.06
    POSITIVE LOGITS
    ==>
    0.07
    .ResponseEntity
    0.07
     urlparse
    0.07
    าณาจ
    0.06
    ",@"
    0.06
    ありがとうござ
    0.06
    нивер
    0.06
    _il
    0.06
    @include
    0.06
     -*-
    0.06
    Act Density 0.004%

    No Known Activations