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

    Neuronpedia

    INDEX
    Explanations

    limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mask
    -0.07
     rebounds
    -0.07
    mmm
    -0.06
     Lit
    -0.06
    加工
    -0.06
    oph
    -0.06
    <-
    -0.06
     prosperity
    -0.06
    Bindings
    -0.06
     人
    -0.06
    POSITIVE LOGITS
     (;;)
    0.06
    messages
    0.06
    reten
    0.06
    чук
    0.06
    reopen
    0.06
    ucher
    0.06
     ελλην
    0.06
     �
    0.06
     »↵↵
    0.06
    raries
    0.06
    Act Density 0.220%

    No Known Activations