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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     &↵
    -0.07
    ATORS
    -0.07
     [(
    -0.06
    Cx
    -0.06
     Negative
    -0.06
    очный
    -0.06
     PRI
    -0.06
     �
    -0.06
    ，在
    -0.06
    uters
    -0.06
    POSITIVE LOGITS
    —the
    0.08
    —with
    0.08
     　　
    0.08
     –
    0.08
    —even
    0.07
    —if
    0.07
    —at
    0.07
    .dup
    0.07
    —for
    0.07
     -
    0.07
    Act Density 0.036%

    No Known Activations