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

    Neuronpedia

    INDEX
    Explanations

    travel independently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">'
    0.44
    ໃຈ
    0.42
     contenuti
    0.42
    ')));
    0.41
    '),('
    0.41
    ])){
    0.40
    Crist
    0.40
    眨
    0.40
    /'
    0.39
    ...'
    0.39
    POSITIVE LOGITS
     Stack
    0.41
     Tract
    0.40
     pyrite
    0.40
     Optimization
    0.40
     Synthesis
    0.38
     Network
    0.37
     diamond
    0.37
     Deformation
    0.37
     homes
    0.37
     Ryu
    0.37
    Act Density 0.000%

    No Known Activations