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

    Neuronpedia

    INDEX
    Explanations

    relationship to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    티
    0.52
    áty
    0.52
    Team
    0.51
    ية
    0.50
    ła
    0.50
     professora
    0.50
    Après
    0.50
     aspett
    0.48
    스
    0.48
    为
    0.47
    POSITIVE LOGITS
    adjustable
    0.50
    اج
    0.45
    arthritis
    0.44
    ogenetic
    0.44
    اکر
    0.42
    autos
    0.41
    verified
    0.40
    crypto
    0.40
    anesu
    0.40
    થે
    0.39
    Act Density 0.001%

    No Known Activations