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

    Neuronpedia

    INDEX
    Explanations

    missiles, muscles, stem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ль
    0.76
    й
    0.70
    ι
    0.68
    reated
    0.63
    <0x80>
    0.62
    ט
    0.62
    स
    0.61
    ि
    0.61
    ufficient
    0.60
    वाइड
    0.60
    POSITIVE LOGITS
     mesmer
    0.63
     escolar
    0.60
    ంబేద్కర్
    0.58
     objeto
    0.57
     episode
    0.55
     FDR
    0.55
     inorder
    0.55
     MND
    0.54
     دائ
    0.53
     публи
    0.52
    Act Density 0.001%

    No Known Activations