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

    Neuronpedia

    INDEX
    Explanations

    this and that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     například
    0.27
     például
    0.24
     örne
    0.22
     isotherms
    0.22
     genitalia
    0.22
    例えば
    0.22
     vigour
    0.22
     catfish
    0.21
     terpen
    0.21
     genitals
    0.21
    POSITIVE LOGITS
     This
    0.35
     Это
    0.34
     That
    0.33
     это
    0.33
     זה
    0.32
    this
    0.32
    Это
    0.31
     THIS
    0.30
     Questo
    0.30
    This
    0.30
    Act Density 3.383%

    No Known Activations