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

    Neuronpedia

    INDEX
    Explanations

    Code keys and strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apasion
    -0.08
     punctual
    -0.08
     electr
    -0.07
     ligand
    -0.07
     relocate
    -0.07
    OTAL
    -0.07
    。而
    -0.07
     relocation
    -0.07
     pase
    -0.07
     enn
    -0.07
    POSITIVE LOGITS
    ,d
    0.08
    luk
    0.08
     chete
    0.08
    erdem
    0.07
     Toby
    0.07
     Consensus
    0.07
     Until
    0.07
    _md
    0.07
    יכון
    0.07
     mümk
    0.07
    Act Density 0.001%

    No Known Activations