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

    Neuronpedia

    INDEX
    Explanations

    meth labs create toxic waste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    im
    0.63
    en
    0.58
    Block
    0.51
    Un
    0.50
    Jeff
    0.50
    Ab
    0.50
    Seal
    0.48
    Front
    0.48
    Vor
    0.48
    ImportGroup
    0.48
    POSITIVE LOGITS
     crossed
    0.51
     wasn
    0.48
     drove
    0.46
     Wouldn
    0.45
     assisted
    0.44
     RSV
    0.44
    0.43
     pleases
    0.43
     nessa
    0.42
     pretended
    0.41
    Act Density 0.004%

    No Known Activations