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

    Neuronpedia

    INDEX
    Explanations

    self- compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.95
    مش
    0.78
     Romana
    0.78
    یدن
    0.77
     Ausgabe
    0.75
     Cou
    0.75
     âm
    0.75
     Unterschied
    0.74
     calcul
    0.73
     ligament
    0.72
    POSITIVE LOGITS
    evident
    1.27
    proclaimed
    1.25
     sufficiency
    1.22
    explanatory
    1.19
    ridges
    1.17
     popOperand
    1.15
    contained
    1.14
     esteem
    1.12
     explanatory
    1.11
    Self
    1.10
    Act Density 0.330%

    No Known Activations