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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leftist
    -0.07
     requestOptions
    -0.07
    不得不说
    -0.07
    十九
    -0.07
    逅
    -0.06
     Slim
    -0.06
     continues
    -0.06
    海岸
    -0.06
    ⽼
    -0.06
    ☾
    -0.06
    POSITIVE LOGITS
     эфф
    0.09
    .attr
    0.07
     abbrev
    0.07
    ﲰ
    0.07
    .mapping
    0.07
     Rew
    0.07
    speech
    0.07
     permissions
    0.07
    _SW
    0.07
    扇
    0.07
    Act Density 0.050%

    No Known Activations