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

    Neuronpedia

    INDEX
    Explanations

    technical/formal context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utilization
    -0.06
     Easy
    -0.06
    acht
    -0.06
    tb
    -0.06
    stud
    -0.06
    uncio
    -0.06
    струк
    -0.06
    Trap
    -0.06
    ôle
    -0.06
    attachments
    -0.06
    POSITIVE LOGITS
    iêng
    0.07
    0.07
    NotBlank
    0.07
    __),
    0.06
    ENSION
    0.06
    (rename
    0.06
     Dmit
    0.06
             ↵
    0.06
    .one
    0.06
     başta
    0.06
    Act Density 0.274%

    No Known Activations