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

    Neuronpedia

    INDEX
    Explanations

    field teams, hardware information, compliance requirement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hrer
    0.39
    otrophic
    0.37
    愕
    0.37
    为主
    0.36
    砶
    0.36
    為主
    0.36
    ̞
    0.36
    ODY
    0.36
    Für
    0.36
    issance
    0.36
    POSITIVE LOGITS
    ifters
    0.40
     recalling
    0.39
     костю
    0.39
     INFORM
    0.38
     recall
    0.38
    calo
    0.38
     Corr
    0.38
     poświę
    0.38
     cosmetic
    0.37
     spines
    0.36
    Act Density 0.001%

    No Known Activations