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

    Neuronpedia

    INDEX
    Explanations

    Lamarckian inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spiders
    0.61
     agak
    0.57
     isnt
    0.56
     atau
    0.56
    ほとんど
    0.56
     doesnt
    0.55
     not
    0.55
     !=
    0.55
     isn
    0.55
     jenis
    0.55
    POSITIVE LOGITS
    ífico
    0.59
    édon
    0.54
    úan
    0.51
    vál
    0.50
    ijdens
    0.50
    provide
    0.49
    PhysRev
    0.49
    FLU
    0.49
    Также
    0.49
    ónico
    0.48
    Act Density 0.395%

    No Known Activations