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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSStringFromClass
    -0.07
     извест
    -0.07
     Usuario
    -0.06
     spoil
    -0.06
    Rotor
    -0.06
    ें,
    -0.06
     пользоват
    -0.06
     Giám
    -0.06
     glBind
    -0.06
     tavern
    -0.06
    POSITIVE LOGITS
     way
    0.07
     happened
    0.07
     eu
    0.07
     -:
    0.07
     worse
    0.06
    aso
    0.06
    ouch
    0.06
    	TokenNameIdentifier
    0.06
    Во
    0.06
     lã
    0.06
    Act Density 0.010%

    No Known Activations