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

    Neuronpedia

    INDEX
    Explanations

    use it well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ement
    0.79
    aal
    0.77
    ać
    0.75
     бойынша
    0.73
    aan
    0.70
    ação
    0.68
    aient
    0.68
    ien
    0.68
    ੀ
    0.68
     poter
    0.66
    POSITIVE LOGITS
    Giải
    0.81
     Buddhism
    0.75
    𝓵
    0.73
     Özel
    0.72
     IOP
    0.71
     findAll
    0.71
    بول
    0.70
    فور
    0.70
     Unsupported
    0.70
     océano
    0.70
    Act Density 0.000%

    No Known Activations