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

    Neuronpedia

    INDEX
    Explanations

    dehydration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spoil
    -0.07
    _pick
    -0.07
    
    -0.07
    sold
    -0.07
    Signup
    -0.07
    neği
    -0.07
    explo
    -0.07
    seys
    -0.06
    administration
    -0.06
    _follow
    -0.06
    POSITIVE LOGITS
     Lab
    0.07
     losses
    0.06
     Against
    0.06
     JT
    0.06
     deleteUser
    0.06
     Lem
    0.06
     wish
    0.06
    .Val
    0.06
    낸
    0.06
     delights
    0.06
    Act Density 0.002%

    No Known Activations