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

    Neuronpedia

    INDEX
    Explanations

    DDR, LPDDR, RAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Scape
    0.46
    Element
    0.44
    Connectivity
    0.44
    แท
    0.43
    Conditional
    0.43
    Register
    0.42
     Differential
    0.42
    Infer
    0.42
    ELD
    0.42
    Mord
    0.42
    POSITIVE LOGITS
     newest
    0.59
     multitudes
    0.57
     rencontres
    0.52
     വിഷയ
    0.51
     woman
    0.50
     que
    0.49
    issionais
    0.49
     qu
    0.49
    ຈັດສົ່ງ
    0.47
     Такие
    0.47
    Act Density 0.000%

    No Known Activations