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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ++]=
    -0.08
     prog
    -0.07
    项目
    -0.06
    Sem
    -0.06
    (vector
    -0.06
     �
    -0.06
    =Y
    -0.06
     ander
    -0.06
    ีม
    -0.06
    (that
    -0.06
    POSITIVE LOGITS
     REP
    0.07
     February
    0.07
     Toast
    0.07
    -city
    0.06
    ToMany
    0.06
     confirmed
    0.06
    profiles
    0.06
     lawmakers
    0.06
    Turning
    0.06
    .device
    0.06
    Act Density 0.000%

    No Known Activations