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

    Neuronpedia

    INDEX
    Explanations

    mathematical problems asking to find the maximum or minimum of something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    652
    -0.06
    bor
    -0.06
    linear
    -0.06
    [c
    -0.06
    elling
    -0.06
    _linear
    -0.05
    antage
    -0.05
     provid
    -0.05
     linear
    -0.05
    Linear
    -0.05
    POSITIVE LOGITS
     Beste
    0.07
    agini
    0.07
     these
    0.07
     takové
    0.07
    iev
    0.06
     RECEIVER
    0.06
     overall
    0.06
     =======
    0.06
    ivent
    0.06
    irit
    0.06
    Act Density 0.040%

    No Known Activations