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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thresholds
    -0.07
    acon
    -0.06
     sensed
    -0.06
     Cosmic
    -0.06
     tomorrow
    -0.06
     uniqu
    -0.06
     faith
    -0.06
     Crack
    -0.06
    	git
    -0.06
    ếp
    -0.06
    POSITIVE LOGITS
    zkum
    0.07
     ilg
    0.07
     ilç
    0.06
    /stdc
    0.06
    _bytes
    0.06
    animals
    0.06
    (UnityEngine
    0.06
    Cong
    0.06
     Rica
    0.06
     क
    0.06
    Act Density 0.000%

    No Known Activations