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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hex
    -0.07
     wake
    -0.07
    代理
    -0.07
    stitution
    -0.06
     trash
    -0.06
    altimore
    -0.06
    omega
    -0.06
    Boston
    -0.06
     vibration
    -0.06
    Population
    -0.06
    POSITIVE LOGITS
     Outside
    0.06
    DrawerToggle
    0.06
    чим
    0.06
    센
    0.06
    resentation
    0.06
     cực
    0.06
    (cmp
    0.06
     pointless
    0.06
     sentient
    0.06
    (layers
    0.06
    Act Density 0.004%

    No Known Activations