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

    Neuronpedia

    INDEX
    Explanations

    variable assignment or initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Phosph
    0.42
     PIA
    0.40
    LLA
    0.40
     அழு
    0.40
    Xi
    0.40
    UTRON
    0.39
    ジ
    0.39
     پتہ
    0.38
    Vive
    0.38
    PSY
    0.38
    POSITIVE LOGITS
     pront
    0.44
     is
    0.43
     providence
    0.42
    scn
    0.41
    ada
    0.40
     legal
    0.39
    acak
    0.39
    hibernate
    0.39
     है
    0.39
     legalized
    0.39
    Act Density 0.031%

    No Known Activations