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

    Neuronpedia

    INDEX
    Explanations

    estimate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belongs
    -0.08
    属性
    -0.07
     attr
    -0.07
    Х
    -0.07
     of
    -0.07
    untary
    -0.07
     with
    -0.07
    武
    -0.06
    对标
    -0.06
    ismatch
    -0.06
    POSITIVE LOGITS
    �
    0.08
     estimates
    0.08
    rigesimal
    0.07
     제품
    0.07
     interceptions
    0.07
    .Rem
    0.07
    --;↵
    0.07
     estimate
    0.07
    阴影
    0.07
    edited
    0.07
    Act Density 0.023%

    No Known Activations