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

    Neuronpedia

    INDEX
    Explanations

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irsch
    -0.07
    ][-
    -0.07
    ▸
    -0.07
    姓
    -0.06
    minus
    -0.06
     [-
    -0.06
    %);↵
    -0.06
    _iters
    -0.06
     Mud
    -0.06
     Terrace
    -0.06
    POSITIVE LOGITS
    支撑
    0.06
    idelberg
    0.06
     supply
    0.06
    关键
    0.06
     tilted
    0.06
    ба
    0.06
     ponto
    0.06
     disruptive
    0.06
    _ANAL
    0.06
    влекатель
    0.06
    Act Density 0.052%

    No Known Activations