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

    Neuronpedia

    INDEX
    Explanations

    probe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    クト
    -0.08
    ूर
    -0.07
    Je
    -0.06
     села
    -0.06
    amento
    -0.06
     Je
    -0.06
     itm
    -0.06
     odpowied
    -0.06
    recursive
    -0.06
    аліст
    -0.06
    POSITIVE LOGITS
     probing
    0.08
    -index
    0.07
     different
    0.07
     Rosenstein
    0.07
     METHODS
    0.07
     Imm
    0.07
     fodder
    0.06
    resources
    0.06
     specifics
    0.06
    ='.$
    0.06
    Act Density 0.006%

    No Known Activations