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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     payroll
    -0.07
     sync
    -0.06
     取
    -0.06
     kind
    -0.06
     move
    -0.06
     shouted
    -0.06
     tweets
    -0.06
     moved
    -0.06
     contaminants
    -0.06
    _Runtime
    -0.06
    POSITIVE LOGITS
    .fromLTRB
    0.07
    ()){
↵
    0.07
     Haram
    0.07
     �
    0.06
     Hasan
    0.06
     Discuss
    0.06
     така
    0.06
     Crus
    0.06
     علي
    0.06
    .CreateIndex
    0.06
    Act Density 0.047%

    No Known Activations