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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stic
    0.40
    coast
    0.38
     दलित
    0.38
     Dusk
    0.38
     জাদু
    0.38
     باسکٹ
    0.37
     聞
    0.37
    リッジ
    0.37
     গণনা
    0.37
    shift
    0.37
    POSITIVE LOGITS
     encom
    0.39
    Diagn
    0.38
     impulso
    0.38
    Diagnostic
    0.37
    Encom
    0.37
    Opinion
    0.37
     conform
    0.37
    乌
    0.37
    Obes
    0.36
    Diagnostics
    0.36
    Act Density 0.001%

    No Known Activations