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

    Neuronpedia

    INDEX
    Explanations

    therapy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     λι
    -0.07
    	cnt
    -0.06
    -colored
    -0.06
    जह
    -0.06
    _ACCEPT
    -0.06
     но
    -0.06
    (Block
    -0.06
    صد
    -0.06
    ваем
    -0.06
    усти
    -0.06
    POSITIVE LOGITS
    unsqueeze
    0.07
     SCIP
    0.07
     específ
    0.07
     option
    0.07
     graduated
    0.06
     Mann
    0.06
     topping
    0.06
     onChange
    0.06
     closure
    0.06
     Kushner
    0.06
    Act Density 0.030%

    No Known Activations