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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pamph
    -0.06
     Uzbek
    -0.06
    _lc
    -0.06
     turret
    -0.06
     alumnos
    -0.06
    atio
    -0.06
     disco
    -0.06
    iswa
    -0.06
     pornôs
    -0.06
    Metro
    -0.05
    POSITIVE LOGITS
    dating
    0.07
     Caval
    0.07
     At
    0.07
    estinal
    0.07
    리는
    0.06
     AppMethodBeat
    0.06
    osphate
    0.06
     Imm
    0.06
    Nom
    0.06
    GridLayout
    0.06
    Act Density 0.005%

    No Known Activations