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

    Neuronpedia

    INDEX
    Explanations

    Code and HTTP requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manga
    -0.08
    剩下的
    -0.06
     下午
    -0.06
     prognosis
    -0.06
     мой
    -0.06
    ruta
    -0.06
     trava
    -0.06
    无疑
    -0.06
     aviation
    -0.06
     bagi
    -0.06
    POSITIVE LOGITS
     attn
    0.07
    overs
    0.06
    言行
    0.06
     bidding
    0.06
     appropriately
    0.06
    iversary
    0.06
    __$
    0.06
    체
    0.06
    不良
    0.06
     defenses
    0.06
    Act Density 0.005%

    No Known Activations