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

    Neuronpedia

    INDEX
    Explanations

    }{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %),
    -0.07
    Membership
    -0.06
     Hä
    -0.06
    -Class
    -0.06
     پرد
    -0.06
     estudiantes
    -0.06
     elt
    -0.06
    -0.06
     برخورد
    -0.06
    Bring
    -0.05
    POSITIVE LOGITS
    猫
    0.07
    autical
    0.07
     disk
    0.07
    -platform
    0.07
    ไป
    0.06
    429
    0.06
    pler
    0.06
    TC
    0.06
     slun
    0.06
    activ
    0.06
    Act Density 0.001%

    No Known Activations