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

    Neuronpedia

    INDEX
    Explanations

    volunteer actions and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activism
    0.51
    डाय
    0.45
    Hire
    0.43
     hire
    0.42
    нови
    0.40
     трудо
    0.40
     Hire
    0.39
    גו
    0.39
    اولة
    0.39
    doctoral
    0.38
    POSITIVE LOGITS
    ism
    0.47
     information
    0.40
     endonuclease
    0.40
     relinqu
    0.39
    istic
    0.38
     Chauhan
    0.38
    atial
    0.38
     firefighters
    0.38
    ithmetic
    0.38
    istische
    0.38
    Act Density 0.002%

    No Known Activations