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

    Neuronpedia

    INDEX
    Explanations

    measurements and text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veterans
    0.52
     metabolismo
    0.51
     prédio
    0.51
     vetor
    0.50
     preexisting
    0.50
     perceives
    0.50
     precludes
    0.50
     menschen
    0.50
     firetruck
    0.49
     rescind
    0.49
    POSITIVE LOGITS
    من
    0.47
    ئ
    0.46
    ulants
    0.42
    mx
    0.41
    nX
    0.41
     Cl
    0.40
    upy
    0.39
    ults
    0.39
    薄
    0.39
    Inv
    0.38
    Act Density 0.001%

    No Known Activations