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

    Neuronpedia

    INDEX
    Explanations

    High overall sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    꾿
    1.34
     ইত্যা
    1.26
    다라고
    1.25
    等が
    1.20
     সকল
    1.18
    等の
    1.16
     నుండి
    1.13
    DataXYZ
    1.10
    ಿಯು
    1.09
     realizar
    1.07
    POSITIVE LOGITS
    .
    1.97
    ."
    1.51
    .”
    1.44
    。
    1.37
    .\
    1.33
    .:
    1.33
    .“
    1.31
    .'
    1.30
    '.
    1.25
    .`
    1.25
    Act Density 0.000%

    No Known Activations