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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्ह
    -0.07
    ップ
    -0.07
     типа
    -0.06
     погляд
    -0.06
    晚
    -0.06
     rfl
    -0.06
    NotificationCenter
    -0.06
    ане
    -0.06
    Cole
    -0.06
    ricao
    -0.06
    POSITIVE LOGITS
    \":\"
    0.07
    광
    0.06
    itches
    0.06
     }}>↵
    0.06
     directions
    0.06
     BLUE
    0.06
     foundations
    0.06
     Identified
    0.06
     salad
    0.06
     invitations
    0.06
    Act Density 0.000%

    No Known Activations