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

    Neuronpedia

    INDEX
    Explanations

    semantic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coe
    -0.07
     Francesco
    -0.07
     deposition
    -0.07
     Fl
    -0.06
    [index
    -0.06
     Circle
    -0.06
    Kyle
    -0.06
    '^
    -0.06
    inspection
    -0.06
     pdb
    -0.06
    POSITIVE LOGITS
    μα
    0.07
     Sanct
    0.06
    اءة
    0.06
     meanings
    0.06
    elan
    0.06
     완
    0.06
    Soap
    0.06
    _prom
    0.06
     awaits
    0.06
    Public
    0.06
    Act Density 0.005%

    No Known Activations