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

    Neuronpedia

    INDEX
    Explanations

    firewall configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smoothing
    -0.08
     rhythms
    -0.08
     Sonn
    -0.08
     autof
    -0.08
    ebab
    -0.08
     sociaal
    -0.07
    .DEBUG
    -0.07
     smoothie
    -0.07
     Rhythm
    -0.07
     subse
    -0.07
    POSITIVE LOGITS
      
    0.09
     circumference
    0.09
     specifies
    0.08
     shekara
    0.08
    _geometry
    0.08
      
    0.08
     protr
    0.08
     pribadi
    0.08
     국가
    0.08
    geometry
    0.08
    Act Density 0.001%

    No Known Activations