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

    Neuronpedia

    INDEX
    Explanations

    projecting onto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     входит
    0.40
    \;\
    0.37
    ♫
    0.36
    を入
    0.36
     входят
    0.36
    kében
    0.35
     memas
    0.35
     کشت
    0.35
     drin
    0.34
    دخل
    0.34
    POSITIVE LOGITS
     onto
    4.16
    onto
    3.42
     Ont
    2.56
    Ont
    2.44
    ONTO
    2.20
     unto
    2.02
     ont
    2.00
    ont
    1.65
     ontology
    1.60
     ontological
    1.48
    Act Density 0.033%

    No Known Activations