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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    новниш
    -0.78
    ništvo
    -0.65
    цездатний
    -0.64
     barbati
    -0.63
     termica
    -0.63
     fevere
    -0.62
     étoit
    -0.62
    interopRequire
    -0.61
     obligé
    -0.59
     purpoſe
    -0.58
    POSITIVE LOGITS
     on
    0.69
     upon
    0.55
     toward
    0.52
    :+:
    0.48
     to
    0.48
     towards
    0.48
     into
    0.48
     played
    0.47
     with
    0.46
     in
    0.46
    Act Density 0.006%

    No Known Activations