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

    Neuronpedia

    INDEX
    Explanations

    depth testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Æ
    -0.09
     לך
    -0.08
     પરિવ
    -0.08
     Braves
    -0.08
     സമൂഹ
    -0.08
    -Shabaab
    -0.08
     ಸಂದರ್ಭ
    -0.08
    ーチ
    -0.08
    .Popen
    -0.08
     تحويل
    -0.08
    POSITIVE LOGITS
    orption
    0.08
     nacht
    0.08
    receive
    0.07
     >>>
    0.07
     climbed
    0.07
     interactions
    0.07
    .receive
    0.07
    eback
    0.07
     semaphore
    0.07
     secon
    0.07
    Act Density 0.000%

    No Known Activations