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

    Neuronpedia

    INDEX
    Explanations

    comparison operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PERATURE
    0.30
     விழுப்பு
    0.30
    Imidazole
    0.29
    टा
    0.27
     ইনডাক
    0.27
    Nú
    0.27
     ไหร่
    0.27
    StillWater
    0.27
    Salve
    0.26
    <unused979>
    0.26
    POSITIVE LOGITS
     the
    0.47
    0.44
     C
    0.38
     F
    0.35
     d
    0.35
     P
    0.34
     N
    0.34
     our
    0.34
     K
    0.33
     S
    0.33
    Act Density 0.387%

    No Known Activations