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

    Neuronpedia

    INDEX
    Explanations

    LIABILITY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虺
    -0.08
    ника
    -0.07
    ern
    -0.07
    ;↵↵↵
    -0.07
     tribute
    -0.07
    谷
    -0.07
    iteur
    -0.07
    влаж
    -0.07
     structure
    -0.07
    句
    -0.07
    POSITIVE LOGITS
    .getExternal
    0.07
    ㌽
    0.07
    errals
    0.07
    잖아요
    0.07
    	answer
    0.07
    Iteration
    0.07
     disparate
    0.07
     behaves
    0.07
    ModelError
    0.07
     LIABILITY
    0.07
    Act Density 0.000%

    No Known Activations