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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inversion
    -0.07
     faults
    -0.07
    των
    -0.06
     які
    -0.06
     ferv
    -0.06
    _full
    -0.06
    τή
    -0.06
     DNS
    -0.06
     '.'
    -0.06
    Spanish
    -0.06
    POSITIVE LOGITS
    EVER
    0.07
     α
    0.07
     prostě
    0.07
     غر
    0.07
     IID
    0.07
    719
    0.07
     Ziel
    0.06
    strength
    0.06
    460
    0.06
     instincts
    0.06
    Act Density 0.024%

    No Known Activations