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

    Neuronpedia

    INDEX
    Explanations

    asynchronous tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    敵
    0.47
    raded
    0.46
    ANDS
    0.45
    తలు
    0.44
    АО
    0.44
    拈
    0.42
    brahim
    0.42
    АР
    0.42
    Cached
    0.42
    敌
    0.42
    POSITIVE LOGITS
     insurer
    0.47
     riguarda
    0.45
    emark
    0.44
    ید
    0.44
    م
    0.43
     insurers
    0.42
    ە
    0.41
     wygląda
    0.41
     dapat
    0.41
     pueblo
    0.41
    Act Density 0.000%

    No Known Activations