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

    Neuronpedia

    INDEX
    Explanations

    volunteering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stone
    -0.07
    )const
    -0.06
     واس
    -0.06
     Streets
    -0.06
    оступ
    -0.06
     hips
    -0.06
     контролю
    -0.06
     consumed
    -0.06
    ulas
    -0.06
    _rx
    -0.06
    POSITIVE LOGITS
    ับท
    0.07
     Decomp
    0.06
    olem
    0.06
    tility
    0.06
    ropolitan
    0.06
    International
    0.06
     stud
    0.06
    โลย
    0.06
     organized
    0.06
    	unset
    0.06
    Act Density 0.033%

    No Known Activations