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

    Neuronpedia

    INDEX
    Explanations

    energetic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     камен
    0.76
     hosszú
    0.73
     dłu
    0.71
     couvre
    0.71
     unprotected
    0.70
     terra
    0.69
     infidelity
    0.68
     chaos
    0.67
     забруд
    0.67
     جميلة
    0.67
    POSITIVE LOGITS
     energetic
    1.11
     Ener
    0.99
     energ
    0.98
     punch
    0.89
     ener
    0.87
     lively
    0.86
    Ener
    0.86
     энерги
    0.84
     dynamic
    0.82
     engaging
    0.82
    Act Density 0.297%

    No Known Activations