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

    Neuronpedia

    INDEX
    Explanations

    not intended to endorse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嚧
    0.43
    Programm
    0.38
    黐
    0.38
     ئەو
    0.38
     Likewise
    0.38
     Bởi
    0.37
    farin
    0.37
    就算
    0.37
     डेब्यू
    0.37
     Logical
    0.37
    POSITIVE LOGITS
     blaming
    0.52
     blame
    0.50
     criticism
    0.49
     criticize
    0.48
     condemnation
    0.47
     argument
    0.47
     intending
    0.47
    폄
    0.46
     propaganda
    0.46
     conjecture
    0.45
    Act Density 0.082%

    No Known Activations