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

    Neuronpedia

    INDEX
    Explanations

    fight-or-flight response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    枧
    0.47
     '".
    0.44
    雩
    0.44
     критери
    0.43
     gradioApp
    0.43
     пище
    0.43
     цвето
    0.42
     '^
    0.42
     Ом
    0.42
    asen
    0.41
    POSITIVE LOGITS
    He
    0.55
    ab
    0.53
    As
    0.52
    It
    0.50
     He
    0.49
    Ab
    0.48
    Okay
    0.48
    ull
    0.46
    he
    0.44
    nb
    0.44
    Act Density 0.000%

    No Known Activations