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

    Neuronpedia

    INDEX
    Explanations

    "iber" or "timber" words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HPO
    0.48
    ASX
    0.47
    Ṕ
    0.47
    smiling
    0.46
    悱
    0.46
    0.45
    ﻭ
    0.45
    𒋾
    0.44
    DMSO
    0.44
    NgramModel
    0.43
    POSITIVE LOGITS
     allow
    0.44
     arm
    0.44
     performance
    0.44
     arcade
    0.44
     sillas
    0.42
     tickets
    0.41
     timber
    0.40
    기에
    0.40
     cabs
    0.40
     band
    0.40
    Act Density 0.007%

    No Known Activations