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

    Neuronpedia

    INDEX
    Explanations

    exodus story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hacerlo
    -0.08
    omega
    -0.08
    angé
    -0.08
    area
    -0.07
    (angle
    -0.07
     ω
    -0.07
    _angle
    -0.07
     பகுத
    -0.07
    .angle
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     oppressed
    0.12
     oppression
    0.11
     persecution
    0.10
     ظلم
    0.09
     oppressive
    0.09
     repression
    0.08
    救世
    0.08
     slavery
    0.08
     Libya
    0.08
     slaves
    0.08
    Act Density 0.006%

    No Known Activations