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

    Neuronpedia

    INDEX
    Explanations

    dale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cons
    -0.07
     Chess
    -0.07
     Thesis
    -0.06
     orth
    -0.06
    Entity
    -0.06
     Letters
    -0.06
     enc
    -0.06
    /close
    -0.06
     scanning
    -0.06
     갈
    -0.06
    POSITIVE LOGITS
     Plaza
    0.07
     confirmation
    0.06
    issenschaft
    0.06
     Kurum
    0.06
    _ELEM
    0.06
     Eduardo
    0.06
    اعد
    0.06
     důvod
    0.06
    影
    0.06
    efault
    0.06
    Act Density 0.000%

    No Known Activations