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

    Neuronpedia

    INDEX
    Explanations

    route to endpoint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Transcript
    0.44
     (++
    0.42
    transcript
    0.41
    nestjs
    0.38
    entities
    0.37
    ილები
    0.37
    dari
    0.37
    CI
    0.36
    Mash
    0.36
    ЦИ
    0.36
    POSITIVE LOGITS
     IMPLIED
    0.42
     करियर
    0.40
    ᄏ
    0.39
     ṣ
    0.39
     spectrometry
    0.37
     nanocom
    0.37
     extrinsic
    0.37
     roadway
    0.37
     проводить
    0.36
     гало
    0.36
    Act Density 0.017%

    No Known Activations