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

    Neuronpedia

    INDEX
    Explanations

    isolation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    theme
    -0.07
    [ch
    -0.06
    engkap
    -0.06
    prech
    -0.06
    chemist
    -0.06
    ップ
    -0.06
    ственное
    -0.06
    XXX
    -0.06
     meng
    -0.06
    enda
    -0.06
    POSITIVE LOGITS
     isolated
    0.16
     isol
    0.15
     isolation
    0.14
     isolate
    0.13
    isol
    0.10
    olated
    0.09
    olation
    0.09
    olate
    0.08
    Io
    0.08
    и
    0.07
    Act Density 0.012%

    No Known Activations