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

    Neuronpedia

    INDEX
    Explanations

    Legal/formal denials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utom
    -0.09
     json
    -0.07
    טלוו
    -0.07
    _roles
    -0.07
     mentally
    -0.07
    pai
    -0.07
    .Classes
    -0.07
    imagen
    -0.07
     Wellington
    -0.07
    JPEG
    -0.07
    POSITIVE LOGITS
    luet
    0.07
    على
    0.07
    osing
    0.07
    	Block
    0.06
    един
    0.06
     <<-
    0.06
    𝙡
    0.06
    ower
    0.06
     yetiştir
    0.06
    흕
    0.06
    Act Density 0.001%

    No Known Activations