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

    Neuronpedia

    INDEX
    Explanations

    Promises or future actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cope
    -0.08
     kinda
    -0.08
     problemática
    -0.08
     нормы
    -0.07
    -0.07
     UUID
    -0.07
     whatever
    -0.07
     tension
    -0.07
     đối
    -0.07
    Underlying
    -0.07
    POSITIVE LOGITS
     Alm
    0.08
     તમને
    0.08
     contigo
    0.08
     tərəfindən
    0.08
     ayudarte
    0.08
    �
    0.08
     qualitative
    0.08
     Stich
    0.07
     proficiency
    0.07
     Dos
    0.07
    Act Density 0.016%
    No Known Activations