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

    Neuronpedia

    INDEX
    Explanations

    /math/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fiscal
    0.39
     బా
    0.38
    arning
    0.38
    ружи
    0.38
    তন
    0.37
    μένη
    0.37
    彩
    0.37
     mengunjungi
    0.37
     डिव
    0.36
    ualmente
    0.36
    POSITIVE LOGITS
    porte
    0.44
    minster
    0.39
    address
    0.38
     addressed
    0.38
     profite
    0.38
    Modes
    0.38
    wins
    0.37
     address
    0.37
     á
    0.37
     stere
    0.37
    Act Density 0.000%

    No Known Activations