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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocusing
    -0.07
     nhớ
    -0.06
     Quiet
    -0.06
    __,__
    -0.06
     stagger
    -0.06
     sanitation
    -0.06
    uffy
    -0.06
    masından
    -0.06
    .area
    -0.06
    -focus
    -0.06
    POSITIVE LOGITS
     influ
    0.07
    (){
↵
    0.07
    Sensor
    0.06
     RID
    0.06
    structor
    0.06
    <Cell
    0.06
    سوب
    0.06
     lokale
    0.06
     Net
    0.06
    Ipv
    0.06
    Act Density 0.044%

    No Known Activations