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

    Neuronpedia

    INDEX
    Explanations

    craft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     վերադարձ
    -0.08
    Captured
    -0.08
    odnev
    -0.08
     produced
    -0.08
     Pere
    -0.08
     dikkat
    -0.08
    ADED
    -0.08
     반환
    -0.07
    ioneel
    -0.07
    .capture
    -0.07
    POSITIVE LOGITS
     location
    0.08
     unlocking
    0.08
     Gro
    0.08
     Linking
    0.08
    location
    0.07
    地点
    0.07
     Assistance
    0.07
     Butter
    0.07
     towering
    0.07
    /general
    0.07
    Act Density 0.005%

    No Known Activations