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

    Neuronpedia

    INDEX
    Explanations

    determine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Appendix
    -0.07
    scopes
    -0.07
    ̈
    -0.07
     compositions
    -0.07
    Tor
    -0.06
     opposes
    -0.06
    .Enc
    -0.06
    Encode
    -0.06
     trapping
    -0.06
     İmpar
    -0.06
    POSITIVE LOGITS
    MOVE
    0.07
    (sock
    0.06
     witches
    0.06
    тож
    0.06
    rač
    0.06
    ,url
    0.06
     pharm
    0.06
     detecting
    0.06
     aborted
    0.06
    fel
    0.06
    Act Density 0.042%

    No Known Activations