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

    Neuronpedia

    INDEX
    Explanations

    apply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .OUT
    -0.07
    thumbs
    -0.06
    _Select
    -0.06
    (Output
    -0.06
     stopwords
    -0.06
     METHODS
    -0.06
     Validation
    -0.06
     Allocation
    -0.06
     waged
    -0.06
     Types
    -0.06
    POSITIVE LOGITS
    疾
    0.07
    ВО
    0.07
    &S
    0.07
    },"
    0.06
    ากร
    0.06
    ười
    0.06
     Amerika
    0.06
    jni
    0.06
     és
    0.06
    회의
    0.06
    Act Density 0.025%

    No Known Activations