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

    Neuronpedia

    INDEX
    Explanations

    something you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nic
    0.52
     Kar
    0.52
     Here
    0.50
     Ko
    0.50
     Knock
    0.49
     piek
    0.49
     Har
    0.49
     Hall
    0.48
     Kas
    0.47
     Vil
    0.47
    POSITIVE LOGITS
    against
    0.54
    songwriter
    0.54
    type
    0.54
     shortcomings
    0.52
    targets
    0.52
    with
    0.51
     contradictions
    0.51
    breakers
    0.50
    targeting
    0.50
    tamil
    0.50
    Act Density 0.000%

    No Known Activations