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

    Neuronpedia

    INDEX
    Explanations

    fully aquatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gestalt
    0.42
    ánsito
    0.41
     emigrated
    0.40
    classlist
    0.40
    phenol
    0.39
     shudder
    0.38
     ama
    0.37
    യായി
    0.37
     tờ
    0.37
    Percy
    0.37
    POSITIVE LOGITS
     UP
    0.44
    覺
    0.41
    耳
    0.40
     Ear
    0.39
     Up
    0.39
     someplace
    0.38
     Diagnose
    0.38
     Explore
    0.38
    覚
    0.38
     SOME
    0.37
    Act Density 0.000%

    No Known Activations