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

    Neuronpedia

    INDEX
    Explanations

    Travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cleanup
    -0.07
     Frame
    -0.07
    ?"↵↵
    -0.07
     ',
    -0.06
    ,’
    -0.06
     proč
    -0.06
    !"↵↵
    -0.06
    谈
    -0.06
     dzieci
    -0.06
    .;
    -0.06
    POSITIVE LOGITS
    arParams
    0.07
     herd
    0.06
     beraber
    0.06
    .flat
    0.06
    bew
    0.06
     studied
    0.06
    remainder
    0.06
     دریا
    0.06
     shadows
    0.06
    legant
    0.06
    Act Density 0.159%

    No Known Activations