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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.74
    erman
    -0.73
    FK
    -0.71
    claw
    -0.69
    EV
    -0.66
    arios
    -0.65
    reci
    -0.65
    Charge
    -0.65
    PO
    -0.64
    Termin
    -0.64
    POSITIVE LOGITS
    theless
    0.84
    olitan
    0.76
    ajor
    0.70
    foundland
    0.67
    icester
    0.65
    ohydrate
    0.64
     Suffolk
    0.64
    ampton
    0.64
    bnb
    0.63
    restling
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.