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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    одатель
    -0.07
    .firebaseapp
    -0.06
    .Qt
    -0.06
    newInstance
    -0.06
     आख
    -0.06
    /s
    -0.06
     Ryder
    -0.06
     wouldn
    -0.06
     advertis
    -0.06
     greet
    -0.06
    POSITIVE LOGITS
     prům
    0.08
    ertext
    0.07
    เผ
    0.07
    roperties
    0.07
    ρο
    0.06
    prises
    0.06
    	sort
    0.06
    lf
    0.06
    cke
    0.06
     wf
    0.06
    Act Density 0.051%

    No Known Activations