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

    Neuronpedia

    INDEX
    Explanations

    talent, people, candidates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⽔
    -0.08
    -pane
    -0.07
     strangely
    -0.07
     heels
    -0.07
    电压
    -0.06
    胖
    -0.06
    +=
    -0.06
     setVisible
    -0.06
     Fuß
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     بإ
    0.07
    因为我们
    0.07
    崩溃
    0.07
    뭄
    0.07
     لإ
    0.07
    borah
    0.07
    lässig
    0.07
    compile
    0.07
    financial
    0.06
    urally
    0.06
    Act Density 0.121%

    No Known Activations