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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tell
    -0.07
    ουσ
    -0.06
    __);
    -0.06
     getting
    -0.06
    .Toggle
    -0.06
    "}}>↵
    -0.06
     Digest
    -0.06
     participating
    -0.06
     demeanor
    -0.06
    Getting
    -0.06
    POSITIVE LOGITS
    そ
    0.07
    lum
    0.06
    *m
    0.06
    超过
    0.06
     ◄
    0.06
    =ax
    0.06
    *d
    0.06
     php
    0.06
    厂
    0.06
    abi
    0.06
    Act Density 0.082%

    No Known Activations