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

    Neuronpedia

    INDEX
    Explanations

    describing 'I' capabilities and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    孫
    0.27
    Specify
    0.27
    David
    0.26
    覺得
    0.26
    ень
    0.25
    क्र
    0.25
     whence
    0.25
    òn
    0.25
    Recent
    0.25
     dubious
    0.25
    POSITIVE LOGITS
     cannot
    0.46
     will
    0.36
     can
    0.34
     strive
    0.33
     aim
    0.33
     lack
    0.31
     are
    0.30
     стара
    0.30
     CAN
    0.30
     try
    0.29
    Act Density 0.029%

    No Known Activations