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

    Neuronpedia

    INDEX
    Explanations

    Colon symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =os
    -0.07
     möglich
    -0.07
    zeros
    -0.07
    肯
    -0.06
    -this
    -0.06
     doubts
    -0.06
    globals
    -0.06
    Broadcast
    -0.06
    	real
    -0.06
     руку
    -0.06
    POSITIVE LOGITS
     cruise
    0.06
     disillusion
    0.06
    .black
    0.06
     mildly
    0.06
    ้↵
    0.06
     verts
    0.06
     ölçüde
    0.06
    _rest
    0.06
     intimately
    0.06
     prim
    0.06
    Act Density 0.001%

    No Known Activations