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

    Neuronpedia

    INDEX
    Explanations

    go for, go to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shumë
    0.30
    auge
    0.27
    ☏
    0.26
    ]+
    0.26
     disini
    0.25
    גם
    0.25
    ைகளையும்
    0.25
                   
    0.24
    Coming
    0.24
    airo
    0.23
    POSITIVE LOGITS
     get
    0.32
    到
    0.32
     to
    0.32
     go
    0.31
     ottenere
    0.29
     가서
    0.28
     find
    0.28
     knocking
    0.28
    跑到
    0.28
     knocked
    0.27
    Act Density 0.007%

    No Known Activations