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

    Neuronpedia

    INDEX
    Explanations

    explaining content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yuan
    0.50
    Princeton
    0.49
    H
    0.46
    toEqual
    0.44
    Å
    0.44
    llen
    0.44
    Henry
    0.43
    JFrame
    0.43
    uo
    0.43
    Carroll
    0.42
    POSITIVE LOGITS
     mitochondrial
    0.59
     damaging
    0.58
     detrimental
    0.57
     sintomas
    0.56
     harmful
    0.55
     disadvantaged
    0.53
     limiting
    0.52
     virus
    0.52
     airborne
    0.52
     categor
    0.51
    Act Density 0.007%

    No Known Activations