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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آغاز
    -0.07
    expand
    -0.06
    Dr
    -0.06
    \Validator
    -0.06
     invite
    -0.06
     nug
    -0.06
     literacy
    -0.06
    -compose
    -0.06
    QUESTION
    -0.06
     judgement
    -0.06
    POSITIVE LOGITS
    =a
    0.07
     :/:
    0.06
     krev
    0.06
    沒
    0.06
    аж
    0.06
     Waterloo
    0.06
     和
    0.06
     ={
    0.06
     glued
    0.06
    _FRONT
    0.06
    Act Density 0.001%

    No Known Activations