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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trillion
    -0.07
     gains
    -0.07
    研究所
    -0.06
     COMMIT
    -0.06
    tre
    -0.06
    _allocate
    -0.06
     prevail
    -0.06
    ут
    -0.06
    USB
    -0.06
    フ
    -0.06
    POSITIVE LOGITS
    vection
    0.07
    pection
    0.07
    angstrom
    0.07
    atego
    0.07
    Česk
    0.06
    implify
    0.06
     rural
    0.06
    (required
    0.06
    .Metro
    0.06
     acclaim
    0.06
    Act Density 0.023%

    No Known Activations