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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OL
    -0.08
    ol
    -0.07
    090
    -0.07
     Bloom
    -0.07
     do
    -0.07
     Cool
    -0.07
     Wool
    -0.07
    04
    -0.07
    chool
    -0.07
    ’ve
    -0.07
    POSITIVE LOGITS
     against
    0.21
     Against
    0.18
    against
    0.17
    Against
    0.14
     tegen
    0.09
     против
    0.08
    atti
    0.08
    Anti
    0.07
     ضد
    0.07
     contra
    0.07
    Act Density 0.022%

    No Known Activations