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

    Neuronpedia

    INDEX
    Explanations

    ready when you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mifflin
    0.79
    врат
    0.76
    دە
    0.75
     Salesforce
    0.75
    ivided
    0.73
    最大の
    0.73
     Ulysses
    0.71
     OneDrive
    0.70
    RB
    0.69
     DOC
    0.69
    POSITIVE LOGITS
    ;
    0.75
    .;
    0.74
    ；
    0.69
    ve
    0.60
    ones
    0.60
    ने
    0.59
     am
    0.59
    ؛
    0.59
     player
    0.58
    .
    0.58
    Act Density 0.106%

    No Known Activations