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

    Neuronpedia

    INDEX
    Explanations

    results, warnings, install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assertThat
    1.35
    going
    1.33
    ीय
    1.33
     thisobject
    1.32
    ⎡
    1.32
    ISSION
    1.30
    下さい
    1.29
     injunctive
    1.28
    établissement
    1.26
    ність
    1.25
    POSITIVE LOGITS
    с
    1.32
    ಿಂದ
    1.23
    𝘤
    1.19
    т
    1.01
    ப்
    0.98
    𝐩
    0.97
     anál
    0.97
    𝘞
    0.96
    сь
    0.95
     rach
    0.95
    Act Density 0.000%

    No Known Activations