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

    Neuronpedia

    INDEX
    Explanations

    technical writing discussing studies and experiments from academic papers or code

    oai_token-act-pair · gemini-2.0-flash

    fulfilling requirements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.65
    tvguidetime
    -0.53
    قایناقلار
    -0.51
    __*/
    -0.50
    TAWA
    -0.50
     Италијани
    -0.47
     ditu
    -0.45
    ISupport
    -0.45
     Schna
    -0.44
    ραγ
    -0.44
    POSITIVE LOGITS
     fulfill
    1.88
     fulfilling
    1.86
     satisfy
    1.85
     fulfills
    1.84
     fulfil
    1.84
     satisfies
    1.81
     fulf
    1.74
     fulfilled
    1.73
     speł
    1.73
     meets
    1.72
    Act Density 4.628%

    No Known Activations