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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kino
    -0.07
     surrounded
    -0.06
     friendship
    -0.06
     Kara
    -0.06
    роч
    -0.06
     Unicorn
    -0.06
     ECM
    -0.06
     newX
    -0.06
    -Bold
    -0.06
    Exc
    -0.06
    POSITIVE LOGITS
    .ResumeLayout
    0.08
    gl
    0.07
     mattresses
    0.06
    ẵng
    0.06
    (il
    0.06
    -show
    0.06
    -book
    0.06
     ims
    0.06
    .now
    0.06
     Patricia
    0.06
    Act Density 0.000%

    No Known Activations