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

    Neuronpedia

    INDEX
    Explanations

    taking advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Humans
    -0.07
    opal
    -0.07
    著
    -0.07
     joven
    -0.07
     res
    -0.07
    {j
    -0.06
     implementation
    -0.06
    _choices
    -0.06
     который
    -0.06
     switch
    -0.06
    POSITIVE LOGITS
     režim
    0.07
     Working
    0.06
     NSObject
    0.06
    “They
    0.06
    ayıf
    0.06
     Constructor
    0.06
    ctor
    0.06
    ueva
    0.06
    owa
    0.06
    ycle
    0.06
    Act Density 0.010%

    No Known Activations