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

    Neuronpedia

    INDEX
    Explanations

    offshore installations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Athens
    -0.07
    cular
    -0.07
     характериз
    -0.07
    �
    -0.07
    _O
    -0.07
     Seller
    -0.06
    στρο
    -0.06
     deceptive
    -0.06
    购
    -0.06
     eminent
    -0.06
    POSITIVE LOGITS
    _ml
    0.06
     indica
    0.06
     OVERRIDE
    0.06
    eless
    0.06
    olated
    0.06
     explosives
    0.06
    etails
    0.06
     Installer
    0.06
    yps
    0.06
    ",&
    0.06
    Act Density 0.017%

    No Known Activations