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

    Neuronpedia

    INDEX
    Explanations

    sip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jump
    -1.09
     Jump
    -0.91
     plunge
    -0.87
    Jump
    -0.85
    jump
    -0.82
    JUMP
    -0.78
     JUMP
    -0.74
     dip
    -0.68
     plunging
    -0.68
     soar
    -0.60
    POSITIVE LOGITS
     дописавши
    0.69
     dna
    0.66
     Epif
    0.66
    DoubleQuotes
    0.61
     AssemblyProduct
    0.58
     StringTokenizer
    0.58
     NSCoder
    0.57
     eventdata
    0.56
     Vorm
    0.55
     melanoma
    0.54
    Act Density 0.130%

    No Known Activations