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

    Neuronpedia

    INDEX
    Explanations

    ost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     hell
    -0.07
     десят
    -0.06
    .walk
    -0.06
     Arrival
    -0.06
     banquet
    -0.06
    IDGET
    -0.06
    ƒ
    -0.06
    accordion
    -0.06
     wilderness
    -0.06
    POSITIVE LOGITS
    proto
    0.06
    客户
    0.06
    .PARAM
    0.06
     anti
    0.06
     Filip
    0.06
     Protector
    0.06
     TS
    0.06
     başlar
    0.06
     Rahman
    0.06
     IDX
    0.06
    Act Density 0.003%

    No Known Activations