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

    Neuronpedia

    INDEX
    Explanations

    images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.56
    Према
    -0.55
    lepiej
    -0.52
     betweenstory
    -0.49
    женские
    -0.46
    красивые
    -0.45
    Lycka
    -0.44
    ̓
    -0.44
     вокруг
    -0.43
    りゃ
    -0.43
    POSITIVE LOGITS
    Istorija
    0.75
    DebuggerStep
    0.71
     OMITBAD
    0.68
     referrerpolicy
    0.63
    tagHelperRunner
    0.61
    帖最后由
    0.57
    fsch
    0.56
    év
    0.56
     AssemblyTitle
    0.55
    XMLSchema
    0.54
    Act Density 0.066%

    No Known Activations