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

    Neuronpedia

    INDEX
    Explanations

    specific descriptions and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    na
    0.49
    Block
    0.49
    Blocks
    0.46
    move
    0.46
     Blocks
    0.45
     Block
    0.45
    ett
    0.44
     Box
    0.44
     Color
    0.43
    Bn
    0.43
    POSITIVE LOGITS
     gonorrhea
    0.57
    ணிய
    0.52
     chiropractor
    0.50
     isoniazid
    0.50
     inflamed
    0.49
     cupcake
    0.49
    mensaje
    0.49
     incriminating
    0.48
     schizophrenia
    0.48
     pube
    0.47
    Act Density 0.000%

    No Known Activations