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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rivers
    -0.07
     Tradition
    -0.07
     Swarm
    -0.06
    Disp
    -0.06
     hazardous
    -0.06
    ্
    -0.06
    (dep
    -0.06
     principalmente
    -0.06
    .bridge
    -0.06
    ]));↵↵
    -0.06
    POSITIVE LOGITS
    ு
    0.07
    LEAR
    0.07
     covered
    0.07
    arching
    0.07
    bor
    0.07
     Brazil
    0.06
    centage
    0.06
     長
    0.06
    _environment
    0.06
    कर
    0.06
    Act Density 0.000%

    No Known Activations