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

    Neuronpedia

    INDEX
    Explanations

    text formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attività
    -0.07
    _OCCURRED
    -0.07
    劳务
    -0.07
    Ὁ
    -0.07
     reluctance
    -0.07
    �
    -0.07
    的趋势
    -0.07
    较大
    -0.06
     своем
    -0.06
    ﻺ
    -0.06
    POSITIVE LOGITS
    -air
    0.07
     Toggle
    0.07
    ategorical
    0.07
    密码
    0.07
    出门
    0.06
    ject
    0.06
    च
    0.06
     Lily
    0.06
     modifies
    0.06
    (%
    0.06
    Act Density 0.032%

    No Known Activations