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

    Neuronpedia

    INDEX
    Explanations

    code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    学院
    -0.07
     alliance
    -0.07
    BYTES
    -0.07
    ọng
    -0.07
     соці
    -0.06
     focal
    -0.06
    Expl
    -0.06
     muted
    -0.06
     cid
    -0.06
    işti
    -0.06
    POSITIVE LOGITS
    vertime
    0.07
    现
    0.07
    IR
    0.07
     forb
    0.06
    computed
    0.06
    (arg
    0.06
     Whatever
    0.06
    şi
    0.06
    áb
    0.06
    sm
    0.06
    Act Density 0.000%

    No Known Activations