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

    Neuronpedia

    INDEX
    Explanations

    insurance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intimate
    -0.07
     mounts
    -0.07
    udget
    -0.07
     onResponse
    -0.07
    BOVE
    -0.06
    nivel
    -0.06
     hidden
    -0.06
    уре
    -0.06
     SIMPLE
    -0.06
    、新
    -0.06
    POSITIVE LOGITS
     electricity
    0.06
     Neil
    0.06
    -il
    0.06
     Дж
    0.06
     IL
    0.06
    rend
    0.06
     WI
    0.06
     visualization
    0.06
    천
    0.06
    -J
    0.06
    Act Density 0.008%

    No Known Activations