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

    Neuronpedia

    INDEX
    Explanations

    Tom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expr
    -0.08
    的话
    -0.07
     Chip
    -0.07
    ca
    -0.06
     존재
    -0.06
    مة
    -0.06
     holes
    -0.06
    ба
    -0.06
     Euler
    -0.06
    údo
    -0.06
    POSITIVE LOGITS
     postage
    0.06
     tarafından
    0.06
     protagonist
    0.06
    	pthread
    0.06
     Oslo
    0.06
     sitcom
    0.06
    -eight
    0.06
    ��
    0.06
    (any
    0.05
     �
    0.05
    Act Density 0.009%

    No Known Activations