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

    Neuronpedia

    INDEX
    Explanations

    water leaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isip
    -0.09
     Kaya
    -0.09
     matchmaking
    -0.08
     shall
    -0.08
    inali
    -0.08
    रीन
    -0.08
     barriers
    -0.08
    าส
    -0.08
     उहाँ
    -0.08
    क्राउ
    -0.08
    POSITIVE LOGITS
    纠
    0.08
     devastated
    0.07
    😭
    0.07
     Wedding
    0.07
    анд
    0.07
     Weddings
    0.07
     desastre
    0.07
     destructive
    0.07
    由于
    0.07
     templates
    0.07
    Act Density 0.007%

    No Known Activations