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

    Neuronpedia

    INDEX
    Explanations

    Heating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    紧密结合
    -0.07
     ")↵
    -0.07
    一家
    -0.07
    PMENT
    -0.07
    ביק
    -0.07
    uguay
    -0.07
     subtract
    -0.07
    ationally
    -0.07
    -dis
    -0.07
    Jan
    -0.07
    POSITIVE LOGITS
    (#
    0.07
    HING
    0.07
     stylesheet
    0.07
    玚
    0.07
     StObject
    0.07
     mik
    0.07
     Uhr
    0.07
    〙
    0.07
     กร
    0.07
    суд
    0.06
    Act Density 0.036%

    No Known Activations