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

    Neuronpedia

    INDEX
    Explanations

    sfc /scannow command

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मूलभूत
    0.55
    betrieb
    0.52
    REIB
    0.51
    Custodian
    0.51
    ponenten
    0.50
     redire
    0.50
     डिवा
    0.49
     बीते
    0.49
     custodians
    0.49
     चोर
    0.48
    POSITIVE LOGITS
    wu
    0.54
    Qq
    0.53
    せい
    0.53
     এক্স
    0.53
    дь
    0.52
     исклю
    0.52
     পোশাক
    0.51
    říklad
    0.51
    롬
    0.50
    蹉
    0.50
    Act Density 0.001%

    No Known Activations