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

    Neuronpedia

    INDEX
    Explanations

    financials, resources, basics, or minutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૦
    0.70
    ０
    0.66
    ১
    0.65
     amerikan
    0.64
     européens
    0.63
    newMessage
    0.62
    ०
    0.62
    龴
    0.60
    भिन्न
    0.59
     schimb
    0.59
    POSITIVE LOGITS
    ).
    0.68
    .
    0.60
    :
    0.57
     .
    0.52
    }.
    0.47
    es
    0.46
    '.
    0.44
     근
    0.44
     prodigious
    0.42
     liberty
    0.42
    Act Density 0.045%

    No Known Activations