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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overhe
    -0.08
    _pitch
    -0.07
     опис
    -0.07
    _slots
    -0.07
    gestellt
    -0.07
    _slot
    -0.07
     commiss
    -0.07
    ailure
    -0.07
    cheduling
    -0.07
     цел
    -0.07
    POSITIVE LOGITS
     approximation
    0.10
    趋
    0.09
     prije
    0.09
     rę
    0.09
     trunc
    0.09
    越来越
    0.09
    	remove
    0.09
     approximate
    0.08
     cutoff
    0.08
     aproxim
    0.08
    Act Density 0.018%

    No Known Activations