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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veloc
    -0.07
    .TextEdit
    -0.07
    よび
    -0.07
     сосуд
    -0.07
     �
    -0.07
    mscorlib
    -0.06
    illy
    -0.06
    
    -0.06
     lekker
    -0.06
     Çin
    -0.06
    POSITIVE LOGITS
     acquiring
    0.06
    .ib
    0.06
     fixed
    0.06
     exploiting
    0.06
     regions
    0.06
     calculating
    0.06
     Overall
    0.06
    /public
    0.06
    availability
    0.06
    (effect
    0.06
    Act Density 0.031%

    No Known Activations