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

    Neuronpedia

    INDEX
    Explanations

    lists of related items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    া
    1.36
    hidrat
    1.22
     aver
    1.18
     mainu
    1.16
     основе
    1.16
     Obi
    1.13
    monium
    1.12
    ljivo
    1.11
    er
    1.10
    ציה
    1.10
    POSITIVE LOGITS
    waveform
    1.47
    pairing
    1.19
    𝒕
    1.18
    ñada
    1.18
    LU
    1.13
    SKI
    1.12
    تماد
    1.12
    encias
    1.12
    atures
    1.11
    ărat
    1.10
    Act Density 0.000%

    No Known Activations