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

    Neuronpedia

    INDEX
    Explanations

    text followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |-
    1.19
    -(-
    1.16
    •
    1.11
    |
    1.11
    电源
    1.10
    –
    1.09
     Rovio
    1.08
    |\
    1.07
    stdlib
    1.06
     cumple
    1.06
    POSITIVE LOGITS
     <<
    0.89
    "><
    0.72
    Hei
    0.72
     Bil
    0.71
     Pub
    0.70
    Pub
    0.69
    acl
    0.67
     бай
    0.66
     bil
    0.63
    omm
    0.62
    Act Density 0.128%

    No Known Activations