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

    Neuronpedia

    INDEX
    Explanations

    suitable for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sell
    0.53
     he
    0.52
     mediast
    0.51
     inh
    0.47
     やす
    0.46
     polluting
    0.46
     conduct
    0.46
    倣
    0.46
     verse
    0.45
     फैला
    0.45
    POSITIVE LOGITS
    shah
    0.61
    r
    0.54
    ر
    0.53
    rist
    0.52
    rst
    0.51
     Chí
    0.49
    league
    0.49
    rij
    0.49
    OUG
    0.49
    ğ
    0.49
    Act Density 0.000%

    No Known Activations