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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    particularly
    -0.08
    TRAN
    -0.07
    .initial
    -0.07
    italize
    -0.07
    ;t
    -0.07
    嬗
    -0.07
    party
    -0.07
    𬶟
    -0.07
    �
    -0.06
     качестве
    -0.06
    POSITIVE LOGITS
    .dylib
    0.07
    商标
    0.07
    ocop
    0.07
    _CFG
    0.07
     negócio
    0.07
    borg
    0.07
    __),
    0.07
     insisting
    0.07
     ม
    0.06
    ();//
    0.06
    Act Density 0.033%

    No Known Activations