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

    Neuronpedia

    INDEX
    Explanations

    inferior, exterior, posterior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monopolist
    0.38
     思い
    0.38
    umlu
    0.38
    ㄲ
    0.38
    shifting
    0.37
    Დ
    0.37
     emblematic
    0.37
    awing
    0.37
    angwa
    0.37
    ట్లా
    0.36
    POSITIVE LOGITS
    ior
    0.90
    iors
    0.88
    IOR
    0.80
    iores
    0.75
    iour
    0.72
    iore
    0.69
    iori
    0.64
    ieur
    0.63
    iora
    0.62
    mediate
    0.61
    Act Density 0.010%

    No Known Activations