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

    Neuronpedia

    INDEX
    Explanations

    could not, cannot read, is not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fonte
    0.41
    ぬ
    0.40
    Madonna
    0.40
    Closeup
    0.39
    Explore
    0.39
    ิศ
    0.38
    DeleteMapping
    0.38
    CreateWall
    0.38
    ਸੀਂ
    0.37
    ologisch
    0.37
    POSITIVE LOGITS
    iax
    0.40
    iac
    0.39
     punt
    0.38
     Mint
    0.38
     CONTIN
    0.36
     Town
    0.36
     Jack
    0.35
     Training
    0.35
     Insider
    0.35
     Chub
    0.35
    Act Density 0.001%

    No Known Activations