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

    Neuronpedia

    INDEX
    Explanations

    Looping through symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一如既
    -0.08
    عباد
    -0.07
    ewire
    -0.07
     lend
    -0.07
     tamb
    -0.07
     שב
    -0.07
     backyard
    -0.06
     Coleman
    -0.06
     educ
    -0.06
     tribute
    -0.06
    POSITIVE LOGITS
    귀
    0.07
     PyTuple
    0.07
     Milf
    0.07
     '';
↵
    0.07
    饱
    0.07
    ':↵↵
    0.07
    工程师
    0.06
    cks
    0.06
    .",
↵
    0.06
    夠
    0.06
    Act Density 0.042%

    No Known Activations