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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replied
    -0.07
    	task
    -0.07
    Accordion
    -0.06
    HP
    -0.06
     getRandom
    -0.06
     Boyd
    -0.06
    .up
    -0.06
    _ma
    -0.06
     limbs
    -0.06
     Fl
    -0.06
    POSITIVE LOGITS
     δύο
    0.08
    (side
    0.07
    την
    0.07
     personne
    0.07
    jury
    0.07
    _Meta
    0.07
    �
    0.07
     {}.
    0.06
     μεγ
    0.06
     отк
    0.06
    Act Density 0.001%

    No Known Activations