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

    Neuronpedia

    INDEX
    Explanations

    Code snippets and technical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    
    -0.07
    gang
    -0.06
     awe
    -0.06
    Throwable
    -0.06
     гал
    -0.06
    caler
    -0.06
    시간
    -0.06
    irse
    -0.06
     decency
    -0.06
    POSITIVE LOGITS
     Prior
    0.07
    ایش
    0.07
     useful
    0.06
     loves
    0.06
    Selective
    0.06
    what
    0.06
    будь
    0.06
    ΙΟΥ
    0.06
    marketing
    0.06
    liquid
    0.06
    Act Density 0.000%

    No Known Activations