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

    Neuronpedia

    INDEX
    Explanations

    animal, secure, pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ologische
    0.43
    мови
    0.43
    inde
    0.42
    groupId
    0.42
    밍
    0.41
    hak
    0.40
     تاج
    0.40
    )}_{\
    0.40
    keme
    0.39
    ⵣ
    0.39
    POSITIVE LOGITS
     Seal
    0.44
     jú
    0.41
     Schreiben
    0.40
     Tick
    0.39
     HOSPITAL
    0.39
     ENGINEERS
    0.39
     EXC
    0.39
     demonstr
    0.39
     Tiger
    0.39
     Quad
    0.38
    Act Density 0.006%

    No Known Activations