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

    Neuronpedia

    INDEX
    Explanations

    JSON structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adsorbed
    0.37
     negatives
    0.36
    Allister
    0.35
    鄰
    0.35
    kin
    0.34
     downright
    0.34
    thereum
    0.33
     valleys
    0.33
    လေး
    0.33
     Appalach
    0.33
    POSITIVE LOGITS
     {}
    0.98
    {}
    0.87
     blah
    0.86
     ....
    0.84
    ・・・。
    0.80
    …?
    0.79
    ..?
    0.79
    ...?
    0.78
     .....
    0.77
    (){}
    0.77
    Act Density 0.073%

    No Known Activations