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

    Neuronpedia

    INDEX
    Explanations

    magnets and clusters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cluster
    -1.09
     Clusters
    -0.95
    Cluster
    -0.90
    Magnetic
    -0.89
     cluster
    -0.88
     חיצוניים
    -0.87
     magnetic
    -0.85
     magnético
    -0.83
     magnétique
    -0.83
     épaules
    -0.82
    POSITIVE LOGITS
    ise
    0.55
    to
    0.53
    ization
    0.53
    ps
    0.51
    cp
    0.51
    coach
    0.50
    c
    0.50
    u
    0.50
    ir
    0.50
    ability
    0.50
    Act Density 0.070%

    No Known Activations