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

    Neuronpedia

    INDEX
    Explanations

    database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     friday
    -0.06
    こんな
    -0.06
     inflicted
    -0.06
     Friday
    -0.06
    Structured
    -0.06
     genera
    -0.06
    blr
    -0.06
    including
    -0.06
    .now
    -0.06
    POSITIVE LOGITS
     showAlert
    0.07
     PyErr
    0.07
    _alignment
    0.07
     Care
    0.06
    .parsers
    0.06
    。www
    0.06
    _grad
    0.06
    _DISABLE
    0.06
     neighbouring
    0.06
     臺
    0.06
    Act Density 0.150%

    No Known Activations