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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igans
    -0.07
    _NC
    -0.06
     presente
    -0.06
     CUT
    -0.06
    quo
    -0.06
     tomto
    -0.05
     čer
    -0.05
    Psi
    -0.05
     endorse
    -0.05
    STER
    -0.05
    POSITIVE LOGITS
    .↵↵↵↵↵↵↵↵
    0.07
    --
↵
    0.07
    '},
↵
    0.07
    FirstOrDefault
    0.07
     itr
    0.07
    ุน
    0.07
     overhaul
    0.07
    },{↵
    0.07
    ез
    0.07
     Feel
    0.07
    Act Density 0.036%

    No Known Activations