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

    Neuronpedia

    INDEX
    Explanations

    eyes, movement, or discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     microscopy
    0.43
     blast
    0.42
     recalled
    0.39
     dead
    0.38
     toxicology
    0.37
     freely
    0.37
     entwick
    0.37
     orch
    0.37
     indict
    0.37
    靘
    0.37
    POSITIVE LOGITS
     обнаружи
    0.46
    類似
    0.41
    rw
    0.39
    Ro
    0.39
    掾
    0.38
    Owl
    0.38
    ke
    0.38
    公民
    0.38
     移動
    0.36
    發現
    0.36
    Act Density 0.001%

    No Known Activations