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

    Neuronpedia

    INDEX
    Explanations

    human origins in universe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ˝
    -0.07
    Ĥ
    -0.07
     terror
    -0.07
    𝐩
    -0.07
     Puppy
    -0.07
    藏着
    -0.06
     Sussex
    -0.06
    Super
    -0.06
    parcel
    -0.06
     elaborate
    -0.06
    POSITIVE LOGITS
     قول
    0.07
    adal
    0.07
    @include
    0.07
    .Val
    0.07
    考試
    0.07
    _OBJ
    0.07
    -sw
    0.06
    иж
    0.06
    _builtin
    0.06
    فال
    0.06
    Act Density 0.092%

    No Known Activations