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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     borr
    -0.09
     Holly
    -0.08
    hurt
    -0.08
     भूल
    -0.08
     collider
    -0.08
     Collider
    -0.08
    jit
    -0.08
    Collider
    -0.08
     Repar
    -0.08
     récol
    -0.08
    POSITIVE LOGITS
    特点
    0.10
     motivations
    0.09
     objectives
    0.09
     size
    0.09
     종류
    0.08
     characteristics
    0.08
     philosophy
    0.08
    Size
    0.08
     considerations
    0.08
     sizes
    0.08
    Act Density 0.206%

    No Known Activations