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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _default
    -0.07
    üm
    -0.07
     někol
    -0.07
    reetings
    -0.07
    xFC
    -0.06
    μμα
    -0.06
     maxSize
    -0.06
    анка
    -0.06
     Babe
    -0.06
     Maher
    -0.06
    POSITIVE LOGITS
     download
    0.06
     sentir
    0.06
     inequalities
    0.06
     protocol
    0.06
     appell
    0.06
     def
    0.06
     отв
    0.05
     cord
    0.05
     Constraints
    0.05
     lud
    0.05
    Act Density 0.004%

    No Known Activations